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

    Neuronpedia

    INDEX
    Explanations

    separator character

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     आरमारा
    0.59
    可谓
    0.54
    ходе
    0.53
    ^{+}$
    0.53
    luxury
    0.52
    多様
    0.49
    educated
    0.49
    झ्या
    0.48
    }^{-}$
    0.48
    decorative
    0.48
    POSITIVE LOGITS
    ,
    1.38
    ،
    1.33
     ,
    1.18
    、
    1.17
     ،
    1.06
    ၊
    1.06
    (),
    1.05
    ，
    1.02
    !,
    1.01
     "",
    0.98
    Act Density 0.538%

    No Known Activations