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

    Neuronpedia

    INDEX
    Explanations

    less, but, competition, initial, irritate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ari
    0.55
     DOG
    0.54
    0.48
    l
    0.46
     vá
    0.45
    uro
    0.43
     va
    0.43
     considerar
    0.42
    ba
    0.42
     averages
    0.42
    POSITIVE LOGITS
    唛
    0.51
    мых
    0.46
     verstär
    0.46
    شع
    0.45
    NumConst
    0.45
    繡
    0.45
    <unused1011>
    0.45
    gateTime
    0.44
    pSensor
    0.44
    ўкі
    0.44
    Act Density 0.003%

    No Known Activations