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

    Neuronpedia

    INDEX
    Explanations

    safety

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    رس
    -0.07
    abela
    -0.06
     apparently
    -0.06
    .Cl
    -0.06
    engo
    -0.06
     котором
    -0.06
     implicated
    -0.06
     كس
    -0.06
    road
    -0.06
    .tensor
    -0.06
    POSITIVE LOGITS
    oggler
    0.07
    antages
    0.07
     Watt
    0.07
    тал
    0.06
    /util
    0.06
    _RESET
    0.06
    (TABLE
    0.06
     SPI
    0.06
    .slf
    0.06
    ิศาสตร
    0.06
    Act Density 0.004%

    No Known Activations