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

    Neuronpedia

    INDEX
    Explanations

    Rex

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     QText
    -0.07
    	sleep
    -0.06
    getDisplay
    -0.06
    벨
    -0.06
     sitcom
    -0.06
    沈
    -0.06
    Flying
    -0.06
    727
    -0.06
    icerca
    -0.06
     مما
    -0.06
    POSITIVE LOGITS
     Harness
    0.08
     x
    0.07
    elder
    0.07
    менно
    0.07
    revolution
    0.07
     (£
    0.07
    ators
    0.06
    较
    0.06
    .TR
    0.06
    θε
    0.06
    Act Density 0.001%

    No Known Activations