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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation, code syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     H
    0.48
    t
    0.47
     I
    0.46
     Sä
    0.45
    h
    0.45
     C
    0.44
    ंपासून
    0.43
    事實
    0.43
     A
    0.43
     is
    0.43
    POSITIVE LOGITS
    ও
    0.59
    ти
    0.54
    пи
    0.53
     wynosi
    0.52
    ना
    0.51
    IMA
    0.51
    ИН
    0.50
    '
    0.50
    Ю
    0.49
    এটি
    0.49
    Act Density 0.003%

    No Known Activations