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

    Neuronpedia

    INDEX
    Explanations

    alg or algorithm

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    '
    2.47
    ע
    1.46
    $
    1.45
    0
    1.38
    \
    1.38
    פ
    1.38
    ה
    1.38
     beş
    1.37
    )
    1.35
    מ
    1.30
    POSITIVE LOGITS
    다면
    1.23
    ية
    1.17
    ٣
    1.11
    as
    1.06
    कालीन
    1.06
    지의
    1.06
    지와
    1.06
    elijk
    1.05
    нес
    1.05
    үз
    1.02
    Act Density 0.000%

    No Known Activations