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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Rab
    -0.07
     gran
    -0.06
    -back
    -0.06
     doctrines
    -0.06
     spi
    -0.06
    왕
    -0.06
    _CC
    -0.06
    )\<
    -0.06
    (com
    -0.06
     Cry
    -0.06
    POSITIVE LOGITS
    texto
    0.07
     ister
    0.07
    noticed
    0.06
    -available
    0.06
    continued
    0.06
     симв
    0.06
    ourcing
    0.06
    ト
    0.06
    IPPING
    0.06
    stanov
    0.06
    Act Density 0.000%

    No Known Activations