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

    Neuronpedia

    INDEX
    Explanations

    defies standard understanding

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    fond
    -0.09
     retrouv
    -0.08
    одно
    -0.08
    őr
    -0.08
     réussir
    -0.08
    rather
    -0.08
     fict
    -0.08
    ضايا
    -0.08
    لاث
    -0.08
    -floor
    -0.07
    POSITIVE LOGITS
     conventional
    0.11
     mundane
    0.11
     accustomed
    0.10
     gewöhn
    0.09
     normale
    0.09
     confines
    0.09
     قواعد
    0.09
     Conventional
    0.09
    传统
    0.09
     convencional
    0.09
    Act Density 0.069%

    No Known Activations