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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .sym
    -0.09
    ’h
    -0.08
    ¹
    -0.07
    <Vertex
    -0.07
    _lat
    -0.07
    InputStream
    -0.07
     ops
    -0.07
     مو
    -0.07
    Spot
    -0.07
    	cv
    -0.06
    POSITIVE LOGITS
    显然
    0.07
     vile
    0.07
    됬
    0.06
     organised
    0.06
     ràng
    0.06
     naming
    0.06
     znaleźć
    0.06
    殛
    0.06
    ustainable
    0.06
    _duplicate
    0.06
    Act Density 0.002%

    No Known Activations