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

    Neuronpedia

    INDEX
    Explanations

    code delimiters like commas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    '],'
    0.82
    "},{"
    0.76
    '),('
    0.73
    "),(
    0.73
    "],"
    0.73
     (-)
    0.66
     (+)
    0.64
     $-$
    0.62
    ˈ
    0.62
    ↵↵↵↵↵↵
    0.61
    POSITIVE LOGITS
    ,
    2.21
    (),
    2.09
    !,
    1.93
    ?,
    1.91
     ,
    1.84
    [],
    1.78
    #,
    1.75
    ،
    1.73
    ₂,
    1.73
    ^{*},
    1.73
    Act Density 0.622%

    No Known Activations