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

    Neuronpedia

    INDEX
    Explanations

    code function definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ны
    0.39
    ，
    0.38
     trono
    0.36
     sábado
    0.35
     със
    0.35
     químicos
    0.35
     от
    0.34
     inviscid
    0.34
     Мо
    0.34
     láp
    0.34
    POSITIVE LOGITS
     can
    0.47
     and
    0.46
    га
    0.39
    and
    0.38
    CH
    0.38
    TA
    0.37
    can
    0.36
    K
    0.36
    ید
    0.36
    ку
    0.34
    Act Density 0.313%

    No Known Activations