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

    Neuronpedia

    INDEX
    Explanations

    mem

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     собой
    -0.07
    Pitch
    -0.07
    stration
    -0.06
    什
    -0.06
     Trek
    -0.06
    �
    -0.06
     görmek
    -0.06
    Rad
    -0.06
     المش
    -0.06
     без
    -0.06
    POSITIVE LOGITS
    fx
    0.07
     сті
    0.07
    	create
    0.07
    least
    0.06
    boys
    0.06
    _xy
    0.06
    бы
    0.06
    xCA
    0.06
    toggle
    0.06
     auctions
    0.06
    Act Density 0.000%

    No Known Activations