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

    Neuronpedia

    INDEX
    Explanations

    the word short

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    1
    0.50
    一些
    0.46
    你
    0.45
    Hoff
    0.45
    2
    0.45
    往
    0.44
    \
    0.44
    prefer
    0.42
    纵
    0.41
    ĺ
    0.41
    POSITIVE LOGITS
     luminal
    0.52
     βασ
    0.51
    avasena
    0.48
     interno
    0.47
     വനി
    0.47
     запла
    0.47
    㥆
    0.47
    စိတ်
    0.46
     cooperating
    0.46
    heira
    0.46
    Act Density 0.005%

    No Known Activations