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

    Neuronpedia

    INDEX
    Explanations

    engine types and fuels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    etext
    0.54
    <0xA1>
    0.52
     журнал
    0.50
    urètre
    0.50
    ecek
    0.49
    макраты
    0.49
     арифмети
    0.48
    ної
    0.48
    ebilir
    0.48
     окно
    0.47
    POSITIVE LOGITS
     Tr
    0.50
     oxid
    0.46
     다시
    0.46
     CORS
    0.45
     Amalfi
    0.44
    ↵↵
    0.43
     Ceramic
    0.42
     Trin
    0.42
     Trojan
    0.42
     À
    0.42
    Act Density 0.002%

    No Known Activations