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

    Neuronpedia

    INDEX
    Explanations

    dumb, Doom, src

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    补偿
    0.46
     powders
    0.45
    garh
    0.43
     powdery
    0.41
    mdi
    0.40
     Powder
    0.39
    inte
    0.38
    Qt
    0.38
    ಂಗ
    0.37
    Pow
    0.37
    POSITIVE LOGITS
    founded
    0.45
     berc
    0.41
    бул
    0.40
    struck
    0.38
     src
    0.38
    drivers
    0.38
    src
    0.37
    цер
    0.36
     griego
    0.36
    winners
    0.36
    Act Density 0.007%

    No Known Activations