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

    Neuronpedia

    INDEX
    Explanations

    4

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ':[
    -0.08
    奖励
    -0.07
     passenger
    -0.07
     )[
    -0.07
    得知
    -0.07
     predict
    -0.07
    endereco
    -0.07
    在此之前
    -0.07
    afe
    -0.07
     ):
    -0.07
    POSITIVE LOGITS
     commonly
    0.07
    蝉
    0.07
     XVI
    0.07
    ⬡
    0.07
    瑗
    0.07
    _UDP
    0.06
    酰
    0.06
     pena
    0.06
     boob
    0.06
    铍
    0.06
    Act Density 0.001%

    No Known Activations