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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    jin
    -0.07
    rx
    -0.06
    _tran
    -0.06
     швид
    -0.06
     Kelvin
    -0.06
     Traff
    -0.06
     burning
    -0.06
     chăm
    -0.06
     WA
    -0.06
     grave
    -0.06
    POSITIVE LOGITS
    ladığı
    0.07
     turquoise
    0.07
    VERSION
    0.07
    -trash
    0.06
    $title
    0.06
    itle
    0.06
    nuts
    0.06
    @media
    0.06
    -tool
    0.06
    _DL
    0.06
    Act Density 0.017%

    No Known Activations