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

    Neuronpedia

    INDEX
    Explanations

    instances of numerical data and percentage-related information

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

    political violence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Pos
    -0.35
    outState
    -0.33
    EN
    -0.31
     bero
    -0.31
    Viki
    -0.31
    ERO
    -0.29
    Читайте
    -0.29
     Palt
    -0.29
    Смотрите
    -0.29
     Pos
    -0.29
    POSITIVE LOGITS
     esternos
    0.84
     informée
    0.74
     ویکی‌آمباردا
    0.72
     ModelExpression
    0.69
    aarrggbb
    0.67
     resourceCulture
    0.65
     BoxDecoration
    0.63
     MainAxisSize
    0.60
    zzleHttp
    0.60
     Мексичка
    0.59
    Act Density 0.018%

    No Known Activations