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

    Neuronpedia

    INDEX
    Explanations

    history

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    mot
    -0.07
    usaha
    -0.06
    arcer
    -0.06
    	effect
    -0.06
    ysi
    -0.06
    asjon
    -0.06
    听起来
    -0.06
    initely
    -0.06
     حيث
    -0.06
    /status
    -0.06
    POSITIVE LOGITS
     Upgrade
    0.07
    ificate
    0.07
     uname
    0.07
     Categoria
    0.07
     dossier
    0.07
     zie
    0.07
    驾驶证
    0.07
     Alberto
    0.07
     hurry
    0.07
    /game
    0.07
    Act Density 0.033%

    No Known Activations