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

    Neuronpedia

    INDEX
    Explanations

    database of responses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ൫
    0.23
    ллин
    0.22
    кин
    0.22
    UseDebug
    0.21
    سرائيل
    0.21
    ㈣
    0.21
    ا۔
    0.20
    Ⲓ
    0.20
    ⠊
    0.20
    ։
    0.20
    POSITIVE LOGITS
    re
    0.37
    il
    0.29
    im
    0.28
    c
    0.28
    J
    0.27
    et
    0.27
    M
    0.26
    ’
    0.26
    “
    0.26
    ed
    0.26
    Act Density 1.302%

    No Known Activations