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

    Neuronpedia

    INDEX
    Explanations

    parentheses/brackets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dental
    -0.07
    cial
    -0.06
    ılığıyla
    -0.06
    》，
    -0.06
    ιά
    -0.06
    [user
    -0.06
     Anthem
    -0.06
    -media
    -0.06
    	product
    -0.06
    ustomer
    -0.06
    POSITIVE LOGITS
    組織
    0.08
    /weather
    0.07
    범
    0.07
    mmo
    0.07
     wy
    0.07
     voi
    0.07
    _invite
    0.07
     Sosyal
    0.06
     fichier
    0.06
     slee
    0.06
    Act Density 0.140%

    No Known Activations