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

    Neuronpedia

    INDEX
    Explanations

    nudity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lying
    -0.06
     Anti
    -0.06
    sty
    -0.06
     `/
    -0.06
     총
    -0.06
    iteli
    -0.06
     Austrian
    -0.06
     Been
    -0.06
     Attached
    -0.06
     значение
    -0.06
    POSITIVE LOGITS
    yellow
    0.07
    LK
    0.07
    инов
    0.07
    #pragma
    0.07
    unchecked
    0.06
    .Execution
    0.06
    Contr
    0.06
    知识
    0.06
    awan
    0.06
    ITUDE
    0.06
    Act Density 0.002%

    No Known Activations