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

    Neuronpedia

    INDEX
    Explanations

    time (minute)

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _NUMBER
    -0.09
    _OPERATOR
    -0.09
     rayon
    -0.08
     Glücksspiel
    -0.08
     Soldier
    -0.08
     rio
    -0.08
     Pics
    -0.08
    読む
    -0.07
    Lire
    -0.07
     dadurch
    -0.07
    POSITIVE LOGITS
     సమావేశ
    0.10
     brief
    0.10
     charla
    0.09
     интервью
    0.09
    Brief
    0.09
     telefonisch
    0.09
    电话
    0.09
     обзор
    0.09
     kısa
    0.09
     briefing
    0.09
    Act Density 0.013%

    No Known Activations