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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .isNotEmpty
    -0.07
     newsletters
    -0.07
    .DB
    -0.07
    奓
    -0.07
    ={},
    -0.06
    .dense
    -0.06
    .Builder
    -0.06
    😳
    -0.06
    _calc
    -0.06
     breeding
    -0.06
    POSITIVE LOGITS
     inhibition
    0.07
    فاد
    0.07
     ":"
    0.07
    ߪ
    0.07
    xz
    0.07
     eks
    0.07
    (Return
    0.06
     tahun
    0.06
     arm
    0.06
    0.06
    Act Density 0.001%

    No Known Activations