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

    Neuronpedia

    INDEX
    Explanations

    existence checks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Với
    -0.08
     separating
    -0.08
     lodge
    -0.08
    件
    -0.08
    這是
    -0.07
     ra
    -0.07
     ship
    -0.07
    still
    -0.07
     fridge
    -0.07
     introduces
    -0.07
    POSITIVE LOGITS
    -result
    0.07
     erotici
    0.07
    "><?
    0.07
     עסקי
    0.07
     Blond
    0.07
    规模化
    0.07
    养老
    0.07
     ogląda
    0.07
     bathtub
    0.07
    🍳
    0.07
    Act Density 0.095%

    No Known Activations