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

    Neuronpedia

    INDEX
    Explanations

    zero

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     calibrated
    -0.08
    elter
    -0.06
    VD
    -0.06
    .controllers
    -0.06
     Patricia
    -0.06
     ++↵
    -0.06
    �
    -0.06
    Buff
    -0.06
     푸
    -0.06
    CNN
    -0.06
    POSITIVE LOGITS
     香港
    0.07
     WARN
    0.06
    _MACRO
    0.06
     आई
    0.06
     ﾉ
    0.06
     Sioux
    0.06
    dub
    0.06
     PyTuple
    0.06
     جم
    0.06
     عملیات
    0.06
    Act Density 0.021%

    No Known Activations