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

    Neuronpedia

    INDEX
    Explanations

    following punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ELEASE
    1.01
    Czas
    0.97
    getImageFolder
    0.97
    龵
    0.96
    χρο
    0.95
    zhihu
    0.95
    つき
    0.95
    loadNpm
    0.95
     probabilmente
    0.93
    Curso
    0.92
    POSITIVE LOGITS
    y
    1.69
    h
    1.50
    י
    1.50
    ל
    1.46
    ו
    1.36
    ル
    1.32
    al
    1.30
    m
    1.30
    le
    1.27
    ing
    1.27
    Act Density 0.001%

    No Known Activations