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

    Neuronpedia

    INDEX
    Explanations

    step to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝑡
    1.10
    AccessException
    1.05
    ً
    1.03
    విధ
    1.01
    vore
    1.00
    descripcion
    1.00
    ی
    1.00
     bakt
    0.97
     récupération
    0.96
    ták
    0.95
    POSITIVE LOGITS
     bilayer
    1.20
     Immutable
    1.16
    ফু
    1.13
     actomyosin
    1.13
    يث
    1.09
    لم
    1.09
     heed
    1.07
    ings
    1.07
     faculty
    1.06
    identifiers
    1.06
    Act Density 0.000%

    No Known Activations