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

    Neuronpedia

    INDEX
    Explanations

    word

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     words
    4.33
     word
    4.25
     Words
    3.93
    word
    3.87
    Words
    3.87
    words
    3.82
    Word
    3.74
     Word
    3.58
     palavras
    3.57
     palavra
    3.46
    POSITIVE LOGITS
    Notification
    0.70
    ധിക
    0.68
    තිය
    0.67
     শৃ
    0.65
    rinde
    0.64
     Notification
    0.62
     untitled
    0.60
    реи
    0.59
     boil
    0.59
    apolitan
    0.59
    Act Density 0.111%

    No Known Activations