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

    Neuronpedia

    INDEX
    Explanations

    requests for user feedback and engagement

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

    leave comments or messages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    KommentareTeilen
    -0.54
    principalColumn
    -0.54
    舺
    -0.54
    Пита
    -0.52
     bezeichneter
    -0.52
    ByVersion
    -0.52
     متحده
    -0.50
    adaptiveStyles
    -0.50
    flute
    -0.50
     DataTypes
    -0.48
    POSITIVE LOGITS
    留言
    0.47
    couvrez
    0.41
     Leave
    0.40
     comment
    0.39
    Leave
    0.37
     leave
    0.36
     cuarzo
    0.35
     comments
    0.34
    Nationalité
    0.33
    ">//
    0.31
    Act Density 0.007%

    No Known Activations