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

    Neuronpedia

    INDEX
    Explanations

    var

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	DEBUG
    -0.06
     xn
    -0.06
    HOUSE
    -0.06
    _Is
    -0.06
    리에
    -0.06
    insics
    -0.06
    oods
    -0.06
    ेग
    -0.06
     niet
    -0.06
    .Our
    -0.06
    POSITIVE LOGITS
     sq
    0.07
     swirl
    0.07
     Wired
    0.06
     Carousel
    0.06
     atmos
    0.06
     вари
    0.06
     devast
    0.06
     pornost
    0.06
     gyro
    0.06
     yiy
    0.06
    Act Density 0.003%

    No Known Activations