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

    Neuronpedia

    INDEX
    Explanations

    span

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     LONG
    -0.08
    Texto
    -0.07
    茭
    -0.07
    江淮
    -0.07
     Offset
    -0.07
     raster
    -0.07
     elementos
    -0.07
    ген
    -0.07
    /content
    -0.07
    ظل
    -0.07
    POSITIVE LOGITS
     honoring
    0.08
    па
    0.07
    吣
    0.07
    女王
    0.07
    jq
    0.07
    илась
    0.07
    IGENCE
    0.07
    ])));↵
    0.07
     comprising
    0.06
     prescribed
    0.06
    Act Density 0.001%

    No Known Activations