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

    Neuronpedia

    INDEX
    Explanations

    words starting with J

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    voren
    0.46
    inud
    0.43
    andfeel
    0.43
    遄
    0.43
    Kamu
    0.43
    რულ
    0.43
    GONDOR
    0.42
    juč
    0.41
     अडचणी
    0.41
     ASSESSMENT
    0.41
    POSITIVE LOGITS
     J
    0.94
    J
    0.86
     j
    0.69
     JM
    0.62
     JL
    0.60
     JD
    0.56
     JT
    0.55
     JP
    0.52
     JC
    0.52
     JSP
    0.52
    Act Density 0.041%

    No Known Activations