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

    Neuronpedia

    INDEX
    Explanations

    ic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    >No
    -0.07
     yummy
    -0.06
    Weights
    -0.06
     bên
    -0.06
    력
    -0.06
    Jeff
    -0.06
     Jeff
    -0.06
     Trend
    -0.06
     体
    -0.06
    noch
    -0.06
    POSITIVE LOGITS
    кти
    0.07
     collects
    0.07
    куля
    0.06
    действ
    0.06
    Divider
    0.06
     JMenuItem
    0.06
    /day
    0.06
    /layout
    0.06
    modifier
    0.06
    літ
    0.06
    Act Density 0.005%

    No Known Activations