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

    Neuronpedia

    INDEX
    Explanations

    programming control flow

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     가지
    0.70
    Acte
    0.63
    🦵
    0.61
    AVOA
    0.59
     venire
    0.59
     և
    0.58
     текста
    0.57
    Toplam
    0.57
     здание
    0.57
    Brun
    0.56
    POSITIVE LOGITS
    er
    1.23
    ar
    1.22
    ing
    1.07
    an
    1.05
    u
    1.04
    a
    1.01
    i
    1.01
    es
    0.99
    ed
    0.99
    o
    0.99
    Act Density 0.261%

    No Known Activations