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

    Neuronpedia

    INDEX
    Explanations

    lists of examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ५
    0.54
    щихся
    0.50
    ጄ
    0.49
    ଜ
    0.45
     സെ
    0.45
    ີ
    0.44
    которы
    0.44
     ಶೆ
    0.44
    ⒏
    0.44
    財
    0.44
    POSITIVE LOGITS
    o
    0.65
    StdHandle
    0.52
    a
    0.51
    e
    0.51
     collider
    0.46
     intestate
    0.45
    et
    0.44
     versione
    0.44
     camshaft
    0.43
    es
    0.42
    Act Density 0.001%

    No Known Activations