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

    Neuronpedia

    INDEX
    Explanations

    Math problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     serv
    -0.07
     成
    -0.07
    -corner
    -0.07
    _motor
    -0.07
    -day
    -0.06
     soothing
    -0.06
     UX
    -0.06
    getY
    -0.06
     placebo
    -0.06
    visitor
    -0.06
    POSITIVE LOGITS
    =function
    0.07
    ाव
    0.07
    	die
    0.06
    .ph
    0.06
    "path
    0.06
    はい
    0.06
    People
    0.06
     Wikispecies
    0.06
    (MenuItem
    0.06
     baja
    0.05
    Act Density 0.024%

    No Known Activations