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

    Neuronpedia

    INDEX
    Explanations

    C/C++ main function argc

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     waiting
    0.46
    Сейчас
    0.43
    uarine
    0.42
     secured
    0.40
     girdle
    0.40
     squeezed
    0.39
     ridden
    0.39
    當時
    0.38
     لپاره
    0.38
    indahan
    0.37
    POSITIVE LOGITS
    з
    0.50
     autres
    0.46
     개의
    0.44
     більш
    0.43
     الج
    0.43
     léger
    0.42
     інших
    0.42
     quelques
    0.41
    شر
    0.41
     жест
    0.41
    Act Density 0.011%

    No Known Activations