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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     الوص
    -0.07
    #define
    -0.07
     irre
    -0.07
     Django
    -0.07
    	sd
    -0.07
    暮
    -0.06
     salario
    -0.06
     roadside
    -0.06
    <hr
    -0.06
    );;↵
    -0.06
    POSITIVE LOGITS
    umni
    0.07
     champs
    0.07
    295
    0.06
    ágenes
    0.06
    ング
    0.06
    _ev
    0.06
    CHOOL
    0.06
    ्यक
    0.06
    ोल
    0.06
    quote
    0.06
    Act Density 0.049%

    No Known Activations