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

    Neuronpedia

    INDEX
    Explanations

    end of sentence punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     jednocześnie
    0.55
     ইতোমধ্যে
    0.47
     infine
    0.46
    /
    0.46
     முதலிய
    0.46
     etcétera
    0.44
     previamente
    0.44
     επίσης
    0.43
    িয়াম
    0.43
    +)$
    0.42
    POSITIVE LOGITS
    ،
    0.60
    !
    0.59
    ।
    0.58
    ។
    0.55
    。
    0.53
    ，
    0.52
    abouts
    0.52
    ։
    0.52
    ။
    0.51
    ,
    0.49
    Act Density 0.511%

    No Known Activations