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

    Neuronpedia

    INDEX
    Explanations

    adverbs ending in ly followed by verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     at
    1.18
     to
    0.96
    ので
    0.80
    おか
    0.76
     ﺍ
    0.75
    お
    0.71
    ،
    0.71
     that
    0.70
     or
    0.69
    مانی
    0.69
    POSITIVE LOGITS
    -
    1.07
    ي
    1.02
    í
    0.93
    us
    0.91
    i
    0.89
    <0x80>
    0.79
    (
    0.79
    <0xB2>
    0.73
    ت
    0.73
    á
    0.70
    Act Density 0.904%

    No Known Activations