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

    Neuronpedia

    INDEX
    Explanations

    confidence or certainty in statements

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

    words of certainty

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rungsseite
    -0.63
     nahilalakip
    -0.61
     <>",
    -0.61
     InputDecoration
    -0.56
    ьаж
    -0.54
     مشين
    -0.52
     resourceCulture
    -0.52
    iress
    -0.50
    mão
    -0.50
     disponibilités
    -0.50
    POSITIVE LOGITS
     definitely
    0.94
     certainly
    0.81
    definitely
    0.77
     surely
    0.74
     zeker
    0.73
     pewno
    0.71
    Definitely
    0.71
     sure
    0.71
     Definitely
    0.69
     certamente
    0.69
    Act Density 0.015%

    No Known Activations