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

    Neuronpedia

    INDEX
    Explanations

    Giving advice

    np_max-act · gemini-2.0-flash

    The neuron fires on multi-syllable abstract nouns (especially plural ones) such as “ways,” “means,” “upsides,” “moments,” or “quality.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    eor
    -0.07
     whoever
    -0.07
     гер
    -0.06
    вий
    -0.06
    _backward
    -0.06
    isEmpty
    -0.06
     eller
    -0.06
     belli
    -0.06
    IAS
    -0.05
    Open
    -0.05
    POSITIVE LOGITS
     Names
    0.07
    saving
    0.07
     revelations
    0.06
     Still
    0.06
     hộ
    0.06
     هد
    0.06
     Ellis
    0.06
    _hidden
    0.06
     Werner
    0.06
    _DH
    0.06
    Act Density 0.148%

    No Known Activations