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

    Neuronpedia

    INDEX
    Explanations

    greater than square root

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    oticons
    0.36
    ريقه
    0.34
     Circles
    0.34
    テーマ
    0.33
     parents
    0.33
    Circles
    0.33
     Lear
    0.32
     attacks
    0.32
    Parents
    0.32
     Filled
    0.31
    POSITIVE LOGITS
    ävät
    0.48
    émie
    0.40
    erné
    0.40
     cancelButton
    0.40
     केशव
    0.39
    钚
    0.39
    ARAJYA
    0.39
     Володи
    0.39
     dépass
    0.38
    czę
    0.38
    Act Density 0.002%

    No Known Activations