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

    Neuronpedia

    INDEX
    Explanations

    Loss

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    boru
    -0.07
    察
    -0.07
     Việt
    -0.07
    .Locale
    -0.07
    sí
    -0.07
    53
    -0.06
     thumbnails
    -0.06
     spelling
    -0.06
    yect
    -0.06
    tti
    -0.06
    POSITIVE LOGITS
    _LO
    0.07
    LIB
    0.06
    (loss
    0.06
    .loss
    0.06
    (rhs
    0.06
    )[-
    0.06
     cuis
    0.06
    orraine
    0.06
    atis
    0.06
    wit
    0.06
    Act Density 0.006%

    No Known Activations