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

    Neuronpedia

    INDEX
    Explanations

    86

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    riday
    -0.07
    signal
    -0.07
     pandas
    -0.06
     trackers
    -0.06
    urd
    -0.06
     retire
    -0.06
    variant
    -0.06
     regulating
    -0.06
    |%
    -0.06
    umbed
    -0.06
    POSITIVE LOGITS
    86
    0.08
    working
    0.07
     교
    0.06
    交
    0.06
     обяз
    0.06
     narcotics
    0.06
    Parm
    0.06
     матери
    0.06
     doorstep
    0.06
    成立
    0.06
    Act Density 0.003%

    No Known Activations