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

    Neuronpedia

    INDEX
    Explanations

    belief

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     eukaryotes
    1.71
     vowels
    1.69
     waiters
    1.56
     secretion
    1.54
     supposed
    1.53
     weaknesses
    1.53
     waterways
    1.53
    ום
    1.52
    多么
    1.52
     graced
    1.50
    POSITIVE LOGITS
    it
    2.41
    ı
    2.31
    ب
    2.27
    p
    2.11
    ä
    2.03
    não
    2.02
    ле
    1.89
    и
    1.89
    ர்
    1.88
    в
    1.84
    Act Density 0.052%

    No Known Activations