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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Abroad
    -0.09
     Graphic
    -0.08
     Successful
    -0.08
     Catalogue
    -0.08
    大奖
    -0.08
     Forecast
    -0.08
    gradable
    -0.08
     watershed
    -0.08
     Influence
    -0.07
     estabelece
    -0.07
    POSITIVE LOGITS
     clandest
    0.09
     unofficial
    0.09
     indist
    0.08
    ，我
    0.08
     consciousness
    0.08
    按照
    0.08
     circumvent
    0.08
     consci
    0.08
     unauthorized
    0.08
     convincing
    0.08
    Act Density 0.011%

    No Known Activations