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

    Neuronpedia

    INDEX
    Explanations

    doing my best

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    क
    0.83
     числен
    0.79
     новые
    0.75
    icción
    0.72
    nál
    0.72
    evoluzione
    0.72
    ्ड
    0.72
    ně
    0.72
     documentos
    0.72
    enquête
    0.71
    POSITIVE LOGITS
    נים
    0.91
     seasoning
    0.75
     garn
    0.73
     noticing
    0.73
     inhaling
    0.73
     oven
    0.71
     plating
    0.70
    🖌
    0.70
     dizzy
    0.68
    ination
    0.67
    Act Density 0.113%

    No Known Activations