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

    Neuronpedia

    INDEX
    Explanations

    technical and multilingual keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    in
    0.61
    il
    0.46
    z
    0.44
     بسبب
    0.43
    m
    0.43
     the
    0.43
    ur
    0.41
     specialty
    0.41
    i
    0.41
    age
    0.40
    POSITIVE LOGITS
     けど
    0.47
    પ્ર
    0.43
     fscanf
    0.42
     qDebug
    0.41
    നിക്ക്
    0.41
    <unused2>
    0.40
     inscreva
    0.40
    ᱔
    0.40
    nyj
    0.40
    дений
    0.40
    Act Density 0.002%

    No Known Activations