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

    Neuronpedia

    INDEX
    Explanations

    specific words and following tokens

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Remainder
    0.41
     outlet
    0.35
     sheets
    0.35
     generators
    0.35
    Outlet
    0.35
     longueur
    0.34
     إِن
    0.34
     consequ
    0.34
    falt
    0.34
     лов
    0.34
    POSITIVE LOGITS
    氳
    0.48
     hello
    0.41
     trắng
    0.41
    hello
    0.38
     White
    0.37
    unier
    0.37
    icado
    0.37
     सफेद
    0.36
     ነ
    0.36
     खेल
    0.35
    Act Density 0.000%

    No Known Activations