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

    Neuronpedia

    INDEX
    Explanations

    idioms, slang, and technical descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tìm
    0.49
     posibles
    0.49
     остров
    0.44
     найбільш
    0.44
     острова
    0.44
     පුද්ග
    0.44
    𝓵
    0.44
    できるように
    0.44
    фона
    0.43
     часа
    0.43
    POSITIVE LOGITS
     金属
    0.42
    禁止
    0.40
    emet
    0.40
     G
    0.38
     BTW
    0.38
     קר
    0.38
    多次
    0.38
     corrosion
    0.38
    ITED
    0.38
     Greg
    0.38
    Act Density 0.013%

    No Known Activations