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

    Neuronpedia

    INDEX
    Explanations

    Whether introducing conditions/alternatives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ции
    1.16
    цию
    0.93
     Determination
    0.84
     Very
    0.82
    вку
    0.82
     برخی
    0.79
     possibilidades
    0.77
    ઓ
    0.77
    Very
    0.77
    ことが
    0.77
    POSITIVE LOGITS
    al
    1.18
    न्
    1.03
    p
    0.98
    ظ
    0.96
    på
    0.95
    л
    0.95
    𐰣
    0.95
    ul
    0.92
    ifest
    0.91
    ро
    0.90
    Act Density 0.001%

    No Known Activations