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

    Neuronpedia

    INDEX
    Explanations

    names of individuals and their respective titles or roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    names followed by biographical details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     crying
    -0.48
     pidiendo
    -0.47
     screaming
    -0.47
     spitting
    -0.44
    TypedDataSet
    -0.41
     spørs
    -0.41
    Viited
    -0.41
     awful
    -0.40
     asking
    -0.40
     blatant
    -0.40
    POSITIVE LOGITS
     graduated
    1.07
     began
    0.84
     studied
    0.83
    Graduated
    0.81
     participated
    0.77
     grew
    0.75
    spent
    0.74
     spent
    0.74
     specializes
    0.73
     started
    0.73
    Act Density 0.051%

    No Known Activations