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

    Neuronpedia

    INDEX
    Explanations

    words starting with O

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ANSAS
    0.39
    WARE
    0.38
     জড়
    0.38
     忄
    0.38
    ።
    0.38
     נו
    0.38
     stopp
    0.38
    ுற
    0.38
    EMENTS
    0.38
     предметы
    0.37
    POSITIVE LOGITS
     O
    0.93
    O
    0.72
    sterreich
    0.66
    paque
    0.57
     О
    0.54
    пределение
    0.54
    pportune
    0.54
    XYGEN
    0.53
     οποίος
    0.53
     Oasis
    0.52
    Act Density 0.046%

    No Known Activations