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

    Neuronpedia

    INDEX
    Explanations

    nat

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    在北京
    -0.08
    .phone
    -0.07
    🍐
    -0.07
    омер
    -0.07
    وي
    -0.07
    /display
    -0.07
    .Company
    -0.07
    掰
    -0.07
    Calc
    -0.07
    checkBox
    -0.06
    POSITIVE LOGITS
     Ct
    0.07
    تفاع
    0.07
     instantiated
    0.07
     Nat
    0.07
     quantitative
    0.07
     regiment
    0.07
    袅
    0.07
    逋
    0.07
    ичество
    0.07
     volatile
    0.07
    Act Density 0.006%

    No Known Activations