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

    Neuronpedia

    INDEX
    Explanations

    indicators of denial or rejection of claims and accusations

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

    refusal or denial

    np_acts-logits-general · gemini-2.0-flash

    negation, denial, refusal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     prochain
    -0.50
    wachs
    -0.48
     Treue
    -0.47
     Either
    -0.46
    +:+
    -0.45
     prossima
    -0.45
     vidéo
    -0.44
    Either
    -0.43
    าก็
    -0.43
     próxima
    -0.43
    POSITIVE LOGITS
    AddTagHelper
    1.01
    ArrowToggle
    0.99
    NameInMap
    0.93
     оригіналу
    0.92
    GraphicsUnit
    0.82
    istoitu
    0.77
    ⓧ
    0.71
     AspNetCore
    0.69
     any
    0.69
    ьаж
    0.69
    Act Density 0.429%

    No Known Activations