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

    Neuronpedia

    INDEX
    Explanations

    override

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    赭
    -0.08
    宫廷
    -0.08
    动感
    -0.08
     fscanf
    -0.08
     Krishna
    -0.08
    全资
    -0.07
     Chanel
    -0.07
    .getExternalStorage
    -0.07
    💁
    -0.07
     shrine
    -0.07
    POSITIVE LOGITS
    遵守
    0.08
    attended
    0.08
     אותם
    0.07
     Deliver
    0.07
     compare
    0.07
    _dict
    0.07
     pp
    0.07
    .stage
    0.07
    见
    0.06
    0.06
    Act Density 0.001%

    No Known Activations