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

    Neuronpedia

    INDEX
    Explanations

    script

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    nox
    -0.06
     cerc
    -0.06
    	z
    -0.06
     mixin
    -0.06
    (\
    -0.06
     settings
    -0.06
    ,width
    -0.06
    _conversion
    -0.06
     lavender
    -0.06
     duck
    -0.06
    POSITIVE LOGITS
    _script
    0.09
    Script
    0.07
    рип
    0.07
     SCRIPT
    0.06
    .classes
    0.06
    amic
    0.06
    _instr
    0.06
    TS
    0.06
    коном
    0.06
    fra
    0.06
    Act Density 0.013%

    No Known Activations