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

    Neuronpedia

    INDEX
    Explanations

    UTF

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    らし
    -0.07
    ulace
    -0.06
    ocrin
    -0.06
    _bl
    -0.06
    ousy
    -0.06
    場合は
    -0.06
     bias
    -0.06
     Malk
    -0.06
    (le
    -0.06
    Ошибка
    -0.06
    POSITIVE LOGITS
     "::
    0.06
     crews
    0.06
    Layer
    0.06
    ologi
    0.06
    ВС
    0.06
    .Refresh
    0.06
     ribbon
    0.06
     mysteries
    0.06
     converged
    0.06
    _processor
    0.06
    Act Density 0.000%

    No Known Activations