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

    Neuronpedia

    INDEX
    Explanations

    separators and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     "";
    0.76
     पीएचडी
    0.72
     `<
    0.72
     [<
    0.69
     $<$
    0.69
     powied
    0.68
     જવાબ
    0.68
    스와
    0.68
     Thrift
    0.67
     ফ
    0.67
    POSITIVE LOGITS
    ,
    1.43
    ,(
    1.17
    !,
    1.10
    ,.
    1.10
    ,..
    1.08
    ,)
    1.05
    ,((
    1.01
    ,=
    1.01
    ,…
    1.00
    ،
    0.98
    Act Density 0.027%

    No Known Activations