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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dol
    -0.07
     decad
    -0.07
    �
    -0.06
     Mandatory
    -0.06
     Lyons
    -0.06
    ONY
    -0.06
    (GET
    -0.06
    	window
    -0.06
     laure
    -0.06
    	last
    -0.06
    POSITIVE LOGITS
    embro
    0.07
     página
    0.06
     Colombian
    0.06
    MM
    0.06
    ês
    0.06
     wur
    0.06
    М
    0.06
    ],
    0.06
     máme
    0.06
     mohli
    0.06
    Act Density 0.000%

    No Known Activations