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

    Neuronpedia

    INDEX
    Explanations

    uses of words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ники
    0.38
    никам
    0.37
    ূলক
    0.36
     Enth
    0.36
     قدیم
    0.36
     promu
    0.35
    PropertyGroup
    0.35
     riferimento
    0.35
     knee
    0.35
     Approaches
    0.35
    POSITIVE LOGITS
     words
    2.47
    words
    2.19
    Words
    2.09
     Words
    2.08
     palabras
    2.02
     palavras
    1.92
     WORDS
    1.90
     woorden
    1.88
     слова
    1.80
     Worte
    1.75
    Act Density 0.041%

    No Known Activations