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

    Neuronpedia

    INDEX
    Explanations

    articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Construction
    -0.07
     Forge
    -0.07
    entar
    -0.07
    .but
    -0.07
     verwenden
    -0.07
    .Build
    -0.07
    GetCurrent
    -0.07
    фи
    -0.06
    ัวร
    -0.06
    gan
    -0.06
    POSITIVE LOGITS
    ',...↵
    0.07
    )>>
    0.06
    -----------↵↵
    0.06
     |
↵
    0.06
    =explode
    0.06
    ทรง
    0.06
    .compile
    0.06
    ::↵↵
    0.06
    {-#
    0.06
    #
↵
    0.06
    Act Density 0.117%

    No Known Activations