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

    Neuronpedia

    INDEX
    Explanations

    sentence end punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    es
    0.26
    かもしれませんが
    0.25
    +,
    0.24
    Sky
    0.23
    Y
    0.23
    がありますが
    0.23
    US
    0.22
    Params
    0.22
    ="",
    0.22
    IN
    0.22
    POSITIVE LOGITS
    ۔
    0.41
    。
    0.41
    ።
    0.40
    ။
    0.38
    .
    0.37
    ।
    0.34
    .。
    0.33
    !.
    0.32
    .!
    0.32
    .”
    0.32
    Act Density 0.382%

    No Known Activations