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

    Neuronpedia

    INDEX
    Explanations

    Updating

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ruta
    -0.06
    	stat
    -0.06
    ollipop
    -0.06
     navigationController
    -0.06
    	record
    -0.06
     comrades
    -0.06
     prob
    -0.06
     delaying
    -0.06
     рек
    -0.06
     ένα
    -0.06
    POSITIVE LOGITS
     Southeast
    0.07
     تلفن
    0.07
    eless
    0.07
     enjoyable
    0.07
     hysteria
    0.07
     bana
    0.06
    andal
    0.06
    abee
    0.06
    浮
    0.06
     okay
    0.06
    Act Density 0.001%

    No Known Activations