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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _vert
    -0.06
    ionale
    -0.06
     linh
    -0.06
    ゴ
    -0.06
    iscrimination
    -0.06
    ência
    -0.06
    —all
    -0.06
    .high
    -0.06
    ولو
    -0.06
    .quant
    -0.06
    POSITIVE LOGITS
    duc
    0.06
     εισ
    0.06
    In
    0.06
    astro
    0.06
    	ON
    0.06
    @n
    0.06
    md
    0.06
     Ebola
    0.06
     maintain
    0.06
    Π
    0.06
    Act Density 0.035%

    No Known Activations