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

    Neuronpedia

    INDEX
    Explanations

    code conditionals/brackets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     The
    -0.08
    限定
    -0.07
     limitada
    -0.07
    招
    -0.07
    キャン
    -0.07
    仪
    -0.07
    地域
    -0.07
    ಾಂ
    -0.07
    实例
    -0.07
     voie
    -0.07
    POSITIVE LOGITS
     encountered
    0.10
    이면
    0.09
    Mientras
    0.09
    mousedown
    0.09
     tecla
    0.09
    keydown
    0.08
     পড়
    0.08
    ientras
    0.08
    mynd
    0.08
     deciding
    0.08
    Act Density 0.014%

    No Known Activations