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

    Neuronpedia

    INDEX
    Explanations

    c

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -common
    -0.07
    φορά
    -0.06
     Pav
    -0.06
    av
    -0.06
    -girl
    -0.06
    /XMLSchema
    -0.06
     underst
    -0.06
    iami
    -0.06
     buds
    -0.06
    agt
    -0.06
    POSITIVE LOGITS
    .Gen
    0.07
    -return
    0.07
    .sign
    0.07
    搜
    0.07
    .cursor
    0.07
    sector
    0.07
    علومات
    0.07
     crawled
    0.06
     مراجع
    0.06
    /ca
    0.06
    Act Density 0.020%

    No Known Activations