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

    Neuronpedia

    INDEX
    Explanations

    district

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     senators
    -0.72
     Senators
    -0.55
    enumi
    -0.54
     senator
    -0.51
    UALA
    -0.47
     vloer
    -0.45
    giai
    -0.44
     anún
    -0.43
     münchen
    -0.43
    actors
    -0.43
    POSITIVE LOGITS
    ---*/
    0.68
    IVEREF
    0.66
    RegressionTest
    0.65
    BeginContext
    0.61
     AssemblyCulture
    0.60
    saraba
    0.59
    JspWriter
    0.59
    Története
    0.57
    ArgsConstructor
    0.57
    CPtr
    0.57
    Act Density 0.036%

    No Known Activations