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

    Neuronpedia

    INDEX
    Explanations

    classification, categorization, statistics, science

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     orchards
    0.56
    MathMarks
    0.55
    িক
    0.52
     awọn
    0.49
     设备
    0.49
     açık
    0.48
     as
    0.48
    ন
    0.48
     hub
    0.47
     emblem
    0.47
    POSITIVE LOGITS
    2
    0.75
    1
    0.65
    adies
    0.56
    Def
    0.54
    多
    0.51
    r
    0.50
    igkeiten
    0.49
    rate
    0.48
     विस्फोटक
    0.48
    分類
    0.47
    Act Density 0.160%

    No Known Activations