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

    Neuronpedia

    INDEX
    Explanations

    aspects features exploring foreigners revolution analyzing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    کو
    0.51
    Deux
    0.50
    Meal
    0.48
    সিদ্ধ
    0.48
    ч
    0.48
    тина
    0.47
    тии
    0.47
    stück
    0.46
    公司的
    0.46
    Fr
    0.46
    POSITIVE LOGITS
     ראש
    0.50
     בע
    0.50
     כ
    0.49
     ata
    0.49
     distribu
    0.48
     pew
    0.48
     sled
    0.47
     כך
    0.47
     על
    0.47
     הראשון
    0.47
    Act Density 0.000%

    No Known Activations