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

    Neuronpedia

    INDEX
    Explanations

    p

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    包括
    -0.07
     jurisdiction
    -0.06
     explode
    -0.06
    ').
    -0.06
    386
    -0.06
     하
    -0.06
    龙
    -0.06
    'nun
    -0.06
     reporters
    -0.06
    leshooting
    -0.06
    POSITIVE LOGITS
     crossed
    0.07
    rocess
    0.06
     boss
    0.06
    Warning
    0.06
    řila
    0.06
    pi
    0.06
    worthy
    0.06
     Richie
    0.06
    Mult
    0.06
    system
    0.06
    Act Density 0.002%

    No Known Activations