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

    Neuronpedia

    INDEX
    Explanations

    links and code comments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    In
    0.44
     ใหญ่
    0.42
    It
    0.42
    Pe
    0.42
     hindi
    0.42
     tohoto
    0.42
     ไม่
    0.41
    ਤੀ
    0.41
     It
    0.41
     incluida
    0.40
    POSITIVE LOGITS
     https
    0.67
     http
    0.59
    https
    0.57
    http
    0.54
     www
    0.43
    ttps
    0.41
     htt
    0.41
     √(
    0.40
    ையடுத்து
    0.39
    hAP
    0.39
    Act Density 0.001%

    No Known Activations