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

    Neuronpedia

    INDEX
    Explanations

    Emotions and personal experiences

    np_max-act · gemini-2.0-flash

    This neuron doesn’t respond to any tokens—it remains inactive and doesn’t detect any particular pattern.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Jason
    -0.07
    _TV
    -0.06
     Andy
    -0.06
     Σα
    -0.06
    dic
    -0.06
    List
    -0.06
     články
    -0.06
     Jason
    -0.06
     Stranger
    -0.06
     dirt
    -0.06
    POSITIVE LOGITS
     erre
    0.06
     wg
    0.06
     pretended
    0.06
    )/(
    0.06
    _TRANS
    0.06
     lobbying
    0.06
    #w
    0.06
    [:,:,
    0.06
    Redis
    0.06
     JUL
    0.06
    Act Density 0.030%

    No Known Activations