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

    Neuronpedia

    INDEX
    Explanations

    code, math operations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _dn
    -0.07
    isdigit
    -0.07
     xn
    -0.06
    LastError
    -0.06
    dsn
    -0.06
    ascular
    -0.06
     coffin
    -0.06
     temptation
    -0.06
    建設
    -0.06
    вар
    -0.06
    POSITIVE LOGITS
     Ext
    0.06
    Forg
    0.06
     restr
    0.06
     vidět
    0.06
     ráno
    0.06
    Church
    0.06
    _ad
    0.06
    fetch
    0.06
     hra
    0.06
     Arth
    0.06
    Act Density 0.027%

    No Known Activations