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

    Neuronpedia

    INDEX
    Explanations

    special characters and punctuation in the text

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

    abstract symbols and formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nahilalakip
    -0.81
     snippetHide
    -0.80
     Signalez
    -0.79
    -0.76
     autorytatywna
    -0.72
     للمعارف
    -0.72
    ſicht
    -0.71
    ﹧
    -0.71
     pinulongan
    -0.71
    adaptiveStyles
    -0.70
    POSITIVE LOGITS
     cereales
    0.32
    FieldNumber
    0.27
    I
    0.27
     темы
    0.27
    langle
    0.25
    uidado
    0.25
     aguacate
    0.25
     ardından
    0.24
    ote
    0.24
     Mangel
    0.23
    Act Density 0.470%

    No Known Activations