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

    Neuronpedia

    INDEX
    Explanations

    words following delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ỉ
    0.47
     한다
    0.46
     แม
    0.44
     punkt
    0.41
    ﾏ
    0.41
    ﾝ
    0.41
     let
    0.40
     doesnt
    0.40
     %.
    0.40
     <=
    0.40
    POSITIVE LOGITS
    statusbar
    0.48
    पिछले
    0.47
    शोर
    0.46
    ひとり
    0.46
    submenu
    0.46
    種類の
    0.45
    कुछ
    0.45
    ための
    0.45
    django
    0.45
    élie
    0.45
    Act Density 0.891%

    No Known Activations