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

    Neuronpedia

    INDEX
    Explanations

    mathbb notation and sets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    werk
    0.68
     superf
    0.68
     జ
    0.64
     ს
    0.63
    úng
    0.61
    orted
    0.60
     á
    0.60
    ából
    0.60
    org
    0.60
    ഗാ
    0.58
    POSITIVE LOGITS
    {~
    0.97
    {
    0.79
    0.76
     Etienne
    0.75
    ዳል
    0.73
    ρακ
    0.72
    <unused512>
    0.72
    έρ
    0.71
    த்திலேயே
    0.70
     Handles
    0.70
    Act Density 0.013%

    No Known Activations