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

    Neuronpedia

    INDEX
    Explanations

    x

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sens
    -0.09
    融资
    -0.07
     dia
    -0.07
     creative
    -0.07
    declare
    -0.07
     pros
    -0.07
     Foto
    -0.07
     dens
    -0.06
     padre
    -0.06
    (http
    -0.06
    POSITIVE LOGITS
    买东西
    0.07
    问问
    0.07
     устрой
    0.07
    חמש
    0.07
    aju
    0.07
    郚
    0.07
    ᑭ
    0.07
    oreach
    0.07
    𝚠
    0.07
    )(↵
    0.07
    Act Density 0.005%

    No Known Activations