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

    Neuronpedia

    INDEX
    Explanations

    repeated, frequent, multiple times

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    р
    0.69
     Р
    0.63
     К
    0.63
     ค
    0.61
     c
    0.60
    <0x80>
    0.57
     juga
    0.57
     ร
    0.56
     sepenuhnya
    0.55
     be
    0.52
    POSITIVE LOGITS
    repeated
    0.76
     repeated
    0.64
     Repeated
    0.62
    反复
    0.56
    繰り返
    0.55
     반복
    0.54
    重复
    0.53
    几次
    0.53
     повторя
    0.52
    repet
    0.52
    Act Density 0.509%

    No Known Activations