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

    Neuronpedia

    INDEX
    Explanations

    code error handling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Metro
    0.79
     Met
    0.77
     ladder
    0.73
     Insulation
    0.71
     HBO
    0.69
     insulation
    0.67
    ุปกรณ์
    0.66
    刂
    0.66
     Ladder
    0.65
    یسر
    0.65
    POSITIVE LOGITS
     캐
    0.67
    kai
    0.67
    ama
    0.66
    ወቅ
    0.65
    캐
    0.63
    পিন
    0.63
     ma
    0.62
    may
    0.62
    SAFE
    0.61
    May
    0.61
    Act Density 0.089%

    No Known Activations