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
    These
    0.41
    天空
    0.36
    Especially
    0.35
    selt
    0.33
    perturb
    0.33
    density
    0.33
    杩
    0.33
    This
    0.33
    utf
    0.33
     discrepancies
    0.32
    POSITIVE LOGITS
    ."
    0.39
    .)
    0.37
    /
    0.36
    이라는
    0.35
    oyu
    0.35
    .",
    0.34
     serait
    0.34
     Guang
    0.34
     pomen
    0.33
     ("
    0.33
    Act Density 0.087%

    No Known Activations