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

    Neuronpedia

    INDEX
    Explanations

    Python code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     expliquer
    0.45
    ەک
    0.42
     diagnóstico
    0.42
     эффек
    0.42
     satiety
    0.41
    Ᏸ
    0.41
     tumeurs
    0.40
     protéines
    0.40
     массы
    0.39
     ingrédients
    0.39
    POSITIVE LOGITS
    if
    0.63
    is
    0.59
    0.59
    on
    0.57
    u
    0.55
    ol
    0.55
    ing
    0.53
    ar
    0.53
    il
    0.53
    l
    0.53
    Act Density 0.192%

    No Known Activations