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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    取り
    -0.07
    Π
    -0.07
     glimpse
    -0.06
    Details
    -0.06
    Meal
    -0.06
     згад
    -0.06
     Ngh
    -0.06
     ارزیابی
    -0.06
    conj
    -0.06
     jin
    -0.06
    POSITIVE LOGITS
    ro
    0.07
    09
    0.06
     چین
    0.06
     Shock
    0.06
     Vegan
    0.06
     adore
    0.06
    clidean
    0.06
     انگ
    0.06
     пенс
    0.06
    -dark
    0.06
    Act Density 0.179%

    No Known Activations