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

    Neuronpedia

    INDEX
    Explanations

    code keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    E
    1.16
    لے
    1.00
    З
    1.00
    П
    0.97
    C
    0.95
    L
    0.95
    R
    0.93
    F
    0.93
     três
    0.90
    X
    0.90
    POSITIVE LOGITS
     หรือ
    1.09
     または
    1.09
    ⁣
    0.91
     or
    0.90
     Расійскай
    0.90
     või
    0.89
     キャ
    0.89
     বা
    0.88
     或
    0.88
    oida
    0.87
    Act Density 0.066%

    No Known Activations