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

    Neuronpedia

    INDEX
    Explanations

    mat

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     align
    -0.06
     trồng
    -0.06
    "",
    -0.06
    .execution
    -0.06
    介绍
    -0.06
     tty
    -0.06
     flipped
    -0.06
     refuses
    -0.06
    lediği
    -0.06
    uego
    -0.06
    POSITIVE LOGITS
    ContentLoaded
    0.07
    wort
    0.07
    Thrown
    0.06
    esda
    0.06
     oci
    0.06
    용
    0.06
    帰
    0.06
     pratique
    0.06
     따
    0.06
     없
    0.06
    Act Density 0.017%

    No Known Activations