Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    secretly

    np_max-act · gemini-2.0-flash

    The neuron activates on adverbial cues of secrecy—especially words signaling hidden or secret motives or desires.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    characters in a storyline who have hidden desires or face internal conflicts regarding their sexuality and relationships.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Cars
    -0.07
    جموع
    -0.06
    Diamond
    -0.06
     provozu
    -0.06
     universal
    -0.06
    (QStringLiteral
    -0.06
    	swap
    -0.06
     эксп
    -0.06
    ENSION
    -0.06
    Selectable
    -0.06
    POSITIVE LOGITS
     secretly
    0.08
     seria
    0.08
     Fireplace
    0.06
     Cave
    0.06
    roperty
    0.06
     Longer
    0.06
     CGRectGet
    0.06
     doubtful
    0.06
     domicile
    0.06
    อร
    0.06
    Act Density 0.008%

    No Known Activations