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

    Neuronpedia

    INDEX
    Explanations

    member of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ك
    1.95
    জ
    1.18
     a
    1.16
    ع
    1.13
    ف
    1.11
    מ
    1.08
    മ
    1.07
    我
    1.05
    '
    1.01
    ני
    1.00
    POSITIVE LOGITS
     members
    1.34
     member
    1.13
     by
    1.03
    ate
    1.02
    t
    1.01
     सदस्यों
    1.00
     integrantes
    0.98
     Members
    0.96
    ور
    0.95
    us
    0.95
    Act Density 0.009%

    No Known Activations