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

    Neuronpedia

    INDEX
    Explanations

    packet type

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tcp
    0.40
     alpha
    0.40
     assi
    0.39
    淦
    0.39
     ByteBuffer
    0.38
     Prediction
    0.38
    ემა
    0.38
     comment
    0.38
     ends
    0.37
     Mes
    0.37
    POSITIVE LOGITS
    printDialog
    0.40
    weiter
    0.39
     हज़ार
    0.37
    ustering
    0.37
    [["
    0.36
    Waar
    0.36
     이차
    0.36
     সদ্য
    0.36
    疾患
    0.35
     diya
    0.35
    Act Density 0.003%

    No Known Activations