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

    Neuronpedia

    INDEX
    Explanations

    code, decode, encode

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ния
    0.77
    ία
    0.69
    чных
    0.64
     聞い
    0.64
    ركه
    0.63
     pecan
    0.63
     splitpos
    0.61
    жение
    0.61
     цены
    0.61
    رت
    0.60
    POSITIVE LOGITS
    I
    0.87
    b
    0.72
    ค
    0.67
    บ
    0.66
    Sub
    0.66
    and
    0.65
    ท
    0.64
    code
    0.60
    。”
    0.59
    h
    0.59
    Act Density 0.000%

    No Known Activations