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

    Neuronpedia

    INDEX
    Explanations

    exception as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ருங்கள்
    0.50
    要是
    0.47
     کبھی
    0.40
    !='
    0.39
     भेंट
    0.39
    ⏮
    0.39
     není
    0.39
     многих
    0.39
     sediments
    0.38
     Bt
    0.38
    POSITIVE LOGITS
    م
    0.49
    ilir
    0.43
    cology
    0.42
    bao
    0.42
     aka
    0.42
    agd
    0.41
     CAP
    0.41
    siye
    0.40
     subsequent
    0.40
     Kast
    0.40
    Act Density 0.008%

    No Known Activations