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

    Neuronpedia

    INDEX
    Explanations

    cannot access something

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Accurate
    -0.07
     steels
    -0.07
     groove
    -0.07
     workmanship
    -0.07
    점을
    -0.07
    Gregorian
    -0.07
     warriors
    -0.07
    kerk
    -0.07
     quantified
    -0.07
    �
    -0.07
    POSITIVE LOGITS
    sandbox
    0.09
     доступа
    0.09
    访问
    0.09
     rechtstreeks
    0.08
     sandbox
    0.08
     аша
    0.08
     Mop
    0.08
     toegang
    0.08
     روب
    0.08
    的网址
    0.08
    Act Density 0.010%

    No Known Activations