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

    Neuronpedia

    INDEX
    Explanations

    website themes and scripts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    |(
    -0.07
     Three
    -0.07
     teacher
    -0.07
     bases
    -0.07
    護
    -0.06
     adviser
    -0.06
    学习
    -0.06
    анные
    -0.06
     sexuality
    -0.06
    จะเป
    -0.06
    POSITIVE LOGITS
    _MR
    0.07
     Gaut
    0.06
     Labor
    0.06
    .isLoading
    0.06
     loads
    0.06
    _chan
    0.06
     bikini
    0.06
    annotations
    0.06
    JUnit
    0.06
    Daily
    0.05
    Act Density 0.088%

    No Known Activations