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

    Neuronpedia

    INDEX
    Explanations

    information, prompts, languages, objects, text, system

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :
    0.38
     number
    0.36
    Dockerfile
    0.36
    Fi
    0.33
    らず
    0.33
    ..
    0.32
    Sa
    0.32
     aantal
    0.32
    s
    0.32
    =
    0.31
    POSITIVE LOGITS
     që
    0.59
     που
    0.56
     мы
    0.55
     שנ
    0.53
     we
    0.52
     التي
    0.52
     они
    0.51
     الذي
    0.50
     שה
    0.50
    ที่คุณ
    0.50
    Act Density 0.070%

    No Known Activations