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

    Neuronpedia

    INDEX
    Explanations

    day

    np_max-act · gemini-2.0-flash

    This neuron detects the discourse marker phrase “at the end of the day,” as used to introduce a concluding or summary statement.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     AttributeSet
    -0.07
    716
    -0.07
     filled
    -0.06
    주소
    -0.06
     Defender
    -0.06
    WINDOW
    -0.06
     bulbs
    -0.06
    んな
    -0.06
    _PERSON
    -0.06
     Bapt
    -0.06
    POSITIVE LOGITS
    Ultimately
    0.09
     내가
    0.07
    jango
    0.07
     заним
    0.07
    ');?>↵
    0.07
    πος
    0.07
    /',↵
    0.07
     Ultimately
    0.06
    .e
    0.06
    oslav
    0.06
    Act Density 0.016%

    No Known Activations