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

    Neuronpedia

    INDEX
    Explanations

    up

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    are
    -0.07
     dividing
    -0.07
     removing
    -0.07
    allele
    -0.07
    Value
    -0.07
     scarce
    -0.07
    gere
    -0.07
    terní
    -0.06
     share
    -0.06
     ratio
    -0.06
    POSITIVE LOGITS
     setup
    0.11
     SETUP
    0.09
     setups
    0.08
    	setup
    0.07
     SetUp
    0.07
    .gui
    0.07
    Webpack
    0.07
     tearDown
    0.07
    help
    0.07
    HU
    0.07
    Act Density 0.019%

    No Known Activations