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

    Neuronpedia

    INDEX
    Explanations

    legal restrictions and considerations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    増
    1.55
    ીએ
    1.52
    িও
    1.51
    ف
    1.48
    ки
    1.41
     IDs
    1.41
    ็ม
    1.39
    ლ
    1.38
    гів
    1.35
     GIFs
    1.34
    POSITIVE LOGITS
    t
    1.87
    ur
    1.63
    ל
    1.52
    ars
    1.50
    ن
    1.48
    ien
    1.46
    è
    1.45
     Rights
    1.45
    ities
    1.41
    as
    1.39
    Act Density 0.314%

    No Known Activations