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

    Neuronpedia

    INDEX
    Explanations

    sections of text that provide specific instructions or guidelines

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

    links and calls to action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dramatique
    -0.26
     ساز
    -0.26
    reactivex
    -0.24
    SuppressMessage
    -0.23
    악
    -0.23
    谁能
    -0.22
    ˈ
    -0.22
     Spisak
    -0.21
     known
    -0.21
     consider
    -0.21
    POSITIVE LOGITS
    Autoritní
    0.79
    SequentialGroup
    0.74
     autorytatywna
    0.73
    contentLoaded
    0.67
     TextAppearance
    0.67
     Wikimedijinoj
    0.66
    Hauptartikel
    0.64
     يتيمه
    0.64
    +#+
    0.63
     препратки
    0.62
    Act Density 0.022%

    No Known Activations