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

    Neuronpedia

    INDEX
    Explanations

    parentheses and braces

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     opat
    -0.06
     Vern
    -0.06
    -desc
    -0.06
     ominous
    -0.06
    Inform
    -0.06
    	next
    -0.06
     bcm
    -0.06
     берег
    -0.06
    	void
    -0.06
    乗
    -0.06
    POSITIVE LOGITS
     vacation
    0.07
    Ads
    0.07
    (abs
    0.07
    _arrays
    0.07
    ケット
    0.07
     espos
    0.06
     phí
    0.06
     masturbating
    0.06
    REST
    0.06
    EY
    0.06
    Act Density 0.008%

    No Known Activations