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

    Neuronpedia

    INDEX
    Explanations

    amin

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     emitter
    -0.07
     RS
    -0.07
    inging
    -0.07
     ammonia
    -0.07
    emode
    -0.06
    ILLED
    -0.06
     Clash
    -0.06
     waged
    -0.06
     гро
    -0.06
    돌
    -0.06
    POSITIVE LOGITS
    向
    0.08
    [v
    0.07
     vitamin
    0.07
    ServletContext
    0.07
    문화
    0.07
     INTERN
    0.07
    "testing
    0.06
     مواطنة
    0.06
    مج
    0.06
    بار
    0.06
    Act Density 0.002%

    No Known Activations