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

    Neuronpedia

    INDEX
    Explanations

    smoothing/filtering

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    OGLE
    -0.07
     adolescent
    -0.06
    низ
    -0.06
     recre
    -0.06
    Muon
    -0.06
    onse
    -0.06
     rubble
    -0.06
    unix
    -0.06
    小姐
    -0.06
     Pharmacy
    -0.06
    POSITIVE LOGITS
     Sarah
    0.07
    :UIControlState
    0.07
     grams
    0.06
     massively
    0.06
     nouvelles
    0.06
    [end
    0.06
    	resolve
    0.06
    ностью
    0.06
    Clear
    0.06
     FIND
    0.06
    Act Density 0.011%

    No Known Activations