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

    Neuronpedia

    INDEX
    Explanations

    America

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    $d
    -0.07
     dinero
    -0.07
    util
    -0.06
    Twig
    -0.06
    vek
    -0.06
     EK
    -0.06
    完成
    -0.06
     mutil
    -0.06
    <stdio
    -0.06
    (Process
    -0.06
    POSITIVE LOGITS
    ONGLONG
    0.06
     алког
    0.06
    (KERN
    0.06
     ред
    0.06
     Mind
    0.06
     PT
    0.06
     scaff
    0.06
     imprison
    0.06
     كه
    0.06
    hpp
    0.06
    Act Density 0.004%

    No Known Activations