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

    Neuronpedia

    INDEX
    Explanations

    fetching or getting data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    0.95
    ol
    0.63
    s
    0.62
    <
    0.60
    <0x80>
    0.59
    س
    0.56
    m
    0.55
     I
    0.54
     E
    0.54
    tä
    0.54
    POSITIVE LOGITS
     ขอ
    0.51
    ει
    0.47
     arquivo
    0.44
    문을
    0.44
     contentService
    0.44
     skapa
    0.43
     roka
    0.43
     своє
    0.43
     njegov
    0.42
     calmer
    0.42
    Act Density 0.304%

    No Known Activations