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

    Neuronpedia

    INDEX
    Explanations

    the "Other"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    il
    0.61
    er
    0.47
    ypter
    0.47
    Affected
    0.45
    >
    0.44
    崞
    0.43
    ilize
    0.42
    itri
    0.42
    :*
    0.42
    olicy
    0.41
    POSITIVE LOGITS
     barang
    0.54
    ﻪ
    0.52
    ǧ
    0.52
     Просто
    0.50
    쿠
    0.50
     friendly
    0.50
     pescado
    0.50
     Европа
    0.49
     సు
    0.49
     sıv
    0.49
    Act Density 0.001%

    No Known Activations