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

    Neuronpedia

    INDEX
    Explanations

    for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    চির
    0.41
    丷
    0.37
     Rxe
    0.35
    价比
    0.35
    ิน
    0.35
    এত
    0.35
    你会
    0.34
    aksanakan
    0.34
    就會
    0.34
     بخوان
    0.34
    POSITIVE LOGITS
     unknown
    2.59
     неизвест
    2.33
    unknown
    2.27
     Unknown
    2.25
    Unknown
    2.17
     unknowns
    2.11
    未知
    2.06
     uncertain
    2.05
     unclear
    2.03
     unsure
    1.98
    Act Density 0.057%

    No Known Activations