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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Taur
    -0.08
     Virgin
    -0.08
     весьма
    -0.08
    iliar
    -0.08
     Втор
    -0.08
     terecht
    -0.08
     cerrado
    -0.08
    controllers
    -0.08
     tegelijkertijd
    -0.08
    хий
    -0.07
    POSITIVE LOGITS
    计算
    0.09
     Calcul
    0.09
     계산
    0.09
    公式
    0.09
     así
    0.09
     FEM
    0.09
     calculated
    0.09
     Calculation
    0.08
    怎么算
    0.08
     calculation
    0.08
    Act Density 0.088%

    No Known Activations