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

    Neuronpedia

    INDEX
    Explanations

    listing additional items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :
    0.34
    issait
    0.26
    ціа
    0.26
     afirmou
    0.26
    σή
    0.24
     BAFF
    0.24
    Avro
    0.23
    єї
    0.23
    Metro
    0.23
    >,</
    0.23
    POSITIVE LOGITS
     עם
    0.52
     with
    0.42
    with
    0.41
     including
    0.38
     also
    0.38
     dengan
    0.38
     также
    0.35
     પણ
    0.35
     avec
    0.34
     včetně
    0.34
    Act Density 0.632%

    No Known Activations