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

    Neuronpedia

    INDEX
    Explanations

    Us

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (App
    -0.07
    χαν
    -0.06
    .Vertical
    -0.06
     حوزه
    -0.06
     compromised
    -0.06
    tha
    -0.06
    광
    -0.06
    .setVisible
    -0.06
     shopping
    -0.06
    ROUT
    -0.06
    POSITIVE LOGITS
    ंड
    0.07
     गई
    0.07
    -ext
    0.07
    اده
    0.07
     Fool
    0.06
     padded
    0.06
     полож
    0.06
    usize
    0.06
     】
    0.06
     Мин
    0.06
    Act Density 0.006%

    No Known Activations