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

    Neuronpedia

    INDEX
    Explanations

    how-to questions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    prefer
    -0.07
     respond
    -0.07
     Triple
    -0.07
    وز
    -0.07
     集
    -0.07
     Hughes
    -0.06
    -reply
    -0.06
    -pay
    -0.06
    уск
    -0.06
     Shades
    -0.06
    POSITIVE LOGITS
    Main
    0.06
    .Companion
    0.06
    .Rad
    0.06
    setParameter
    0.06
    ?>
    0.06
     Export
    0.05
     '.')
    0.05
     loginUser
    0.05
    ']?>
    0.05
     ČR
    0.05
    Act Density 0.013%

    No Known Activations