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

    Neuronpedia

    INDEX
    Explanations

    comments and references to user interface elements in programming code

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

    button handler

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    o
    -1.08
    ה
    -0.75
    oes
    -0.73
    y
    -0.72
    yos
    -0.71
     vir
    -0.71
    maki
    -0.70
    ộng
    -0.68
    RESOLVED
    -0.68
     EFF
    -0.67
    POSITIVE LOGITS
    paravant
    0.97
     geheim
    0.85
    ValueStyle
    0.85
     égal
    0.79
    saraba
    0.78
    abetes
    0.76
     وتسجيلات
    0.75
    Примечания
    0.75
     anonim
    0.75
     kefir
    0.74
    Act Density 0.036%

    No Known Activations