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

    Neuronpedia

    INDEX
    Explanations

    guard

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    AIN
    -0.07
    pain
    -0.06
    _TASK
    -0.06
    Used
    -0.06
     Erotische
    -0.06
     pregunta
    -0.06
     tenga
    -0.06
     neuroscience
    -0.06
     erotica
    -0.06
     errorHandler
    -0.06
    POSITIVE LOGITS
     expected
    0.07
    stantiateViewController
    0.07
    "↵↵
    0.06
     disappointed
    0.06
    <Transform
    0.06
     masculinity
    0.06
     surprised
    0.06
     इतन
    0.06
     Festival
    0.06
     surprise
    0.06
    Act Density 0.020%

    No Known Activations