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

    Neuronpedia

    INDEX
    Explanations

    languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Incident
    0.90
    ა
    0.86
     Deals
    0.86
    ت
    0.84
     дії
    0.82
    apsack
    0.82
    由
    0.82
     Modules
    0.82
    আমি
    0.80
     сход
    0.79
    POSITIVE LOGITS
    ção
    0.85
    wohl
    0.81
    toBeTruthy
    0.78
    ូល
    0.77
    ธุ์
    0.77
    šla
    0.75
    り
    0.74
    heartedly
    0.73
    いた
    0.72
    smithy
    0.70
    Act Density 0.000%

    No Known Activations