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

    Neuronpedia

    INDEX
    Explanations

    | symbol followed by conjunction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    /
    1.63
     /
    1.45
    -/
    1.36
    等を
    1.36
    /,
    1.35
    ,/
    1.34
    /.
    1.33
    ／
    1.33
    ﹑
    1.32
    、
    1.26
    POSITIVE LOGITS
     maupun
    1.52
     AND
    1.30
     lẫn
    1.26
     OR
    1.12
     OF
    1.06
    AND
    1.05
    OF
    0.99
    OR
    0.95
     as
    0.88
     FOR
    0.87
    Act Density 0.275%

    No Known Activations