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

    Neuronpedia

    INDEX
    Explanations

    OR

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    уществ
    -0.07
     rl
    -0.07
     Kemp
    -0.07
    _dy
    -0.06
    conditional
    -0.06
    enario
    -0.06
    泳
    -0.06
    _y
    -0.06
     movers
    -0.06
    presence
    -0.06
    POSITIVE LOGITS
    CGRect
    0.08
     brat
    0.07
    Sugar
    0.06
     iceberg
    0.06
     json
    0.06
     výše
    0.06
    _eval
    0.06
     производства
    0.06
    SMART
    0.06
    朵
    0.06
    Act Density 0.001%

    No Known Activations