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

    Neuronpedia

    INDEX
    Explanations

    words starting with letters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     rect
    0.38
     brigades
    0.35
     spi
    0.35
     посту
    0.35
     implication
    0.35
     trase
    0.35
     erect
    0.34
     competitivo
    0.34
     pharmacy
    0.34
     శి
    0.34
    POSITIVE LOGITS
     alphabetically
    1.02
     alphabetical
    0.88
    alphabet
    0.82
     alphabet
    0.82
    Alphabet
    0.80
     Alphabet
    0.75
     alfabet
    0.71
     алфа
    0.70
    字母
    0.61
     acronym
    0.58
    Act Density 0.051%

    No Known Activations