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

    Neuronpedia

    INDEX
    Explanations

    DOI links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ﾚ
    0.65
     antit
    0.65
     странах
    0.60
     thermoplastics
    0.60
     Venezuel
    0.59
     जो
    0.59
     ਹੀ
    0.58
    𝔯
    0.58
     몸
    0.58
     किंवा
    0.57
    POSITIVE LOGITS
    ang
    0.70
    _
    0.67
    ęcia
    0.66
    {
    0.62
    ktiv
    0.60
    čina
    0.59
    (
    0.59
    de
    0.58
    عين
    0.58
    Avec
    0.58
    Act Density 0.001%

    No Known Activations