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

    Neuronpedia

    INDEX
    Explanations

    Source

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Centrale
    -0.09
    	pthread
    -0.08
     hilfre
    -0.08
     Turin
    -0.08
     disturbances
    -0.08
     Center
    -0.08
     المركز
    -0.08
     Aussagen
    -0.08
     coher
    -0.08
     lashes
    -0.08
    POSITIVE LOGITS
    イント
    0.09
     vehicles
    0.08
     clan
    0.08
     nations
    0.08
    .dll
    0.08
     ongeloof
    0.08
     véhicules
    0.07
     novels
    0.07
    Adventure
    0.07
    ід
    0.07
    Act Density 0.004%

    No Known Activations