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

    Neuronpedia

    INDEX
    Explanations

    "auth" configuration parameters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    r
    1.55
    ي
    1.52
    ა
    1.29
    .
    1.25
    I
    1.23
    t
    1.21
    ী
    1.20
    en
    1.20
    ing
    1.17
    y
    1.17
    POSITIVE LOGITS
     desconocido
    1.15
     були
    1.13
    ला
    1.10
     obligatorio
    1.10
    ુ
    1.09
     privacidad
    1.06
     profundo
    1.04
     complicado
    1.03
     supuesto
    1.00
    று
    0.97
    Act Density 0.007%

    No Known Activations