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

    Neuronpedia

    INDEX
    Explanations

    academic/technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    textbox
    -0.07
    _frame
    -0.06
     Lite
    -0.06
    (token
    -0.06
     neat
    -0.06
    <B
    -0.06
    ategori
    -0.06
    tile
    -0.06
     умов
    -0.06
    џџџџџџџџ
    -0.06
    POSITIVE LOGITS
    -dev
    0.07
     lực
    0.07
    ุตร
    0.06
    λα
    0.06
    -char
    0.06
     senza
    0.06
    kami
    0.06
    チ
    0.06
    )}}"
    0.06
    ?>">
    0.06
    Act Density 0.112%

    No Known Activations