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

    Neuronpedia

    INDEX
    Explanations

    science and technology

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    When
    -0.07
     spite
    -0.07
     Verde
    -0.06
     Loud
    -0.06
     QTest
    -0.06
    携
    -0.06
    Meanwhile
    -0.06
    /export
    -0.06
    _and
    -0.06
    ाथ
    -0.06
    POSITIVE LOGITS
    .predict
    0.07
     sz
    0.07
    PUTE
    0.07
     aggrav
    0.06
    PLUGIN
    0.06
    (be
    0.06
     وح
    0.06
     허
    0.06
    .RELATED
    0.06
     والح
    0.06
    Act Density 0.183%

    No Known Activations