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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .getNum
    -0.08
    responses
    -0.07
    pter
    -0.07
     gays
    -0.07
    ey
    -0.07
    postgres
    -0.07
    -password
    -0.06
     plut
    -0.06
    .toByteArray
    -0.06
     Peng
    -0.06
    POSITIVE LOGITS
    續
    0.07
     Certainly
    0.06
     Corpor
    0.06
    结束
    0.06
     terminating
    0.06
    THR
    0.06
     unleashed
    0.06
    ~~~~~~~~
    0.06
    _Main
    0.06
    �
    0.06
    Act Density 0.004%

    No Known Activations