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

    Neuronpedia

    INDEX
    Explanations

    emergency numbers and years

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     variable
    0.73
     পারে
    0.66
     Variable
    0.66
    ၎
    0.64
     stopwatch
    0.63
    டுகளை
    0.63
     linearly
    0.62
    Dmat
    0.61
     аппарат
    0.61
     ticker
    0.61
    POSITIVE LOGITS
    NEWS
    0.91
    News
    0.84
     NEWS
    0.83
     बजकर
    0.78
    eight
    0.77
    news
    0.76
     eleven
    0.75
     تمت
    0.75
    த்ய
    0.74
     News
    0.74
    Act Density 0.100%

    No Known Activations