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

    Neuronpedia

    INDEX
    Explanations

    Future posts/articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tịch
    -0.07
    (method
    -0.06
     credible
    -0.06
     trolling
    -0.06
     CET
    -0.06
     skutečnosti
    -0.06
    iedades
    -0.06
    (up
    -0.06
     EVENT
    -0.06
    Sh
    -0.06
    POSITIVE LOGITS
    .Panel
    0.07
    ;")↵
    0.07
    ;};↵
    0.07
    ();}↵
    0.07
    !")↵
    0.06
    }",↵
    0.06
    .ColumnHeadersHeightSizeMode
    0.06
    íž
    0.06
    '}>↵
    0.06
    ])↵↵
    0.06
    Act Density 0.026%

    No Known Activations