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

    Neuronpedia

    INDEX
    Explanations

    LaTeX fractions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     aspectos
    0.44
    ेंडर
    0.42
    Belarus
    0.41
    फ्र
    0.41
    ⵔ
    0.41
    nder
    0.41
     ASPECTS
    0.40
    غانستان
    0.39
    Speakers
    0.39
    ლა
    0.39
    POSITIVE LOGITS
    ia
    0.44
    {}{
    0.43
    }}{\
    0.43
    }}{
    0.40
     Bernoulli
    0.39
     Had
    0.39
     {
    0.38
     Can
    0.37
     Exercise
    0.37
     Bef
    0.37
    Act Density 0.006%

    No Known Activations