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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    urations
    -0.07
    inning
    -0.07
     вперед
    -0.07
     componentWillUnmount
    -0.06
     Been
    -0.06
     dosy
    -0.06
    و
    -0.06
     genitals
    -0.06
     остров
    -0.06
     двад
    -0.06
    POSITIVE LOGITS
     blank
    0.07
    -exclusive
    0.07
     esper
    0.06
    884
    0.06
     rect
    0.06
     lender
    0.06
    icerca
    0.06
    تص
    0.06
     proprio
    0.06
     zajist
    0.06
    Act Density 0.001%

    No Known Activations