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

    Neuronpedia

    INDEX
    Explanations

    all information or comprehensive document

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    4
    0.72
    5
    0.61
     initiale
    0.61
    6
    0.54
     aktuelle
    0.52
     licz
    0.51
    <0xDA>
    0.50
    1
    0.50
     lokale
    0.49
     individuelle
    0.49
    POSITIVE LOGITS
    elbe
    0.51
    ToString
    0.48
    éct
    0.46
    ónicas
    0.45
     ಏ
    0.43
     thereof
    0.42
    OrderBy
    0.42
    ería
    0.41
    それ
    0.41
    ूरी
    0.41
    Act Density 0.001%

    No Known Activations