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

    Neuronpedia

    INDEX
    Explanations

    articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     States
    -0.07
    mes
    -0.07
    Codes
    -0.07
    最
    -0.07
    хи
    -0.07
    arts
    -0.06
    ds
    -0.06
     firms
    -0.06
    Devices
    -0.06
     ventas
    -0.06
    POSITIVE LOGITS
     neurop
    0.07
    ธน
    0.06
    ycopg
    0.06
     dormant
    0.06
    	Namespace
    0.06
     tam
    0.06
    PARATOR
    0.06
    lilik
    0.06
     numel
    0.06
    _secret
    0.06
    Act Density 0.151%

    No Known Activations