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

    Neuronpedia

    INDEX
    Explanations

    other words and programming constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    »
    0.41
    NVIC
    0.39
     »
    0.37
    <0x81>
    0.37
    coli
    0.37
     United
    0.36
    া
    0.35
    prom
    0.35
    viable
    0.35
    United
    0.35
    POSITIVE LOGITS
     其他
    0.44
     일반
    0.42
     остальные
    0.40
     খাওয়ার
    0.40
    其余
    0.39
     остальных
    0.39
     অন্যান্য
    0.39
     다른
    0.39
     macer
    0.39
     параметр
    0.39
    Act Density 0.110%

    No Known Activations