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

    Neuronpedia

    INDEX
    Explanations

    Fig

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    [index
    -0.07
    .Metro
    -0.07
     RAD
    -0.07
     baja
    -0.06
     Т
    -0.06
    _SC
    -0.06
     india
    -0.06
    entifier
    -0.06
     FAA
    -0.06
    靠
    -0.06
    POSITIVE LOGITS
     Conc
    0.07
    $↵↵
    0.07
    (pg
    0.07
     With
    0.07
     obsess
    0.06
    》，
    0.06
    uddle
    0.06
     explaining
    0.06
     Bere
    0.06
    /raw
    0.06
    Act Density 0.001%

    No Known Activations