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

    Neuronpedia

    INDEX
    Explanations

    statistics and locations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (optimizer
    -0.07
    .With
    -0.07
    .You
    -0.07
    """
    -0.06
    fortawesome
    -0.06
    imes
    -0.06
     grpc
    -0.06
    初始化
    -0.06
    ˆ
    -0.06
    .msg
    -0.06
    POSITIVE LOGITS
    PED
    0.08
     dön
    0.07
    .Done
    0.06
    _ATTACH
    0.06
    .StackTrace
    0.06
     Sachs
    0.06
     Fare
    0.06
     동일
    0.06
     сел
    0.06
     Abdullah
    0.06
    Act Density 0.005%

    No Known Activations