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

    Neuronpedia

    INDEX
    Explanations

    names of people and entities related to cultural or historical significance

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

    names of people and places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Signalez
    -0.79
     Wicidata
    -0.73
     Walkover
    -0.72
     HasFactory
    -0.68
     समीक्षाओं
    -0.67
    InjectAttribute
    -0.67
     surla
    -0.66
    دانشنامهٔ
    -0.65
    <unused41>
    -0.65
    <pad>
    -0.65
    POSITIVE LOGITS
     partout
    0.25
     havia
    0.25
     perdiendo
    0.23
     había
    0.23
     bune
    0.23
    ngdoc
    0.23
     tava
    0.23
    目
    0.23
    GNUC
    0.22
     maïs
    0.22
    Act Density 0.045%

    No Known Activations