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

    Neuronpedia

    INDEX
    Explanations

    expressing interest

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ک
    0.86
    า
    0.79
    ява
    0.71
     Island
    0.70
     Institute
    0.70
    𝕚
    0.70
    ുമ്പോൾ
    0.68
    ুন
    0.67
    mathcal
    0.66
    ු
    0.66
    POSITIVE LOGITS
    ’
    0.73
    га
    0.66
    刮
    0.66
    ”
    0.61
    一张
    0.60
     税
    0.60
    \
    0.60
    ш
    0.60
    સ્ક
    0.59
    brun
    0.58
    Act Density 0.002%

    No Known Activations