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

    Neuronpedia

    INDEX
    Explanations

    lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    on
    0.66
    s
    0.56
    a
    0.55
    T
    0.55
    P
    0.55
    R
    0.55
    b
    0.54
    N
    0.54
    p
    0.51
    B
    0.51
    POSITIVE LOGITS
     국내
    0.52
    ету
    0.51
     актив
    0.50
     सक्रिय
    0.50
    öv
    0.50
     объявления
    0.49
    ímica
    0.49
     descuentos
    0.49
    getCql
    0.46
    )¶
    0.46
    Act Density 0.000%

    No Known Activations