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

    Neuronpedia

    INDEX
    Explanations

    closing punctuation followed by new sentence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ان
    0.43
    न
    0.43
    ন
    0.39
    ن
    0.37
    }_{+}
    0.36
    ncnc
    0.36
    on
    0.36
    ర
    0.34
    as
    0.33
    ra
    0.33
    POSITIVE LOGITS
     in
    0.71
     an
    0.48
    も
    0.45
     be
    0.43
    도
    0.41
     I
    0.41
    在
    0.40
     and
    0.40
    지
    0.39
     nine
    0.39
    Act Density 0.000%

    No Known Activations