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

    Neuronpedia

    INDEX
    Explanations

    HTML select elements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lift
    -0.07
    ewear
    -0.07
    winner
    -0.07
     reflection
    -0.07
     bacteria
    -0.06
    emaker
    -0.06
    witter
    -0.06
     rotor
    -0.06
    -La
    -0.06
     hostname
    -0.06
    POSITIVE LOGITS
     taşım
    0.06
     giy
    0.06
     insanın
    0.06
    俺
    0.06
     臺
    0.06
     vedle
    0.06
     客
    0.06
    (rowIndex
    0.06
     누
    0.06
    	unit
    0.06
    Act Density 0.075%

    No Known Activations