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

    Neuronpedia

    INDEX
    Explanations

    economic, Flights, RSI, risk, Speech

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     watcher
    0.50
    ากหลาย
    0.48
     watchlist
    0.47
     WORTH
    0.46
    わた
    0.46
    اتب
    0.45
    balik
    0.45
    ็ง
    0.44
    পরিস
    0.44
    ಂಡ್
    0.44
    POSITIVE LOGITS
     If
    0.57
     It
    0.54
     Box
    0.53
     On
    0.52
     Mounting
    0.52
     Mount
    0.51
     Detailed
    0.50
    ine
    0.50
     Having
    0.50
     I
    0.49
    Act Density 0.001%

    No Known Activations