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

    Neuronpedia

    INDEX
    Explanations

    polymers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    encrypt
    -0.07
     modifiers
    -0.07
    ieces
    -0.07
     Abyss
    -0.07
     hely
    -0.07
    سلام
    -0.07
     Olsen
    -0.07
    епти
    -0.07
    (equal
    -0.07
     prefix
    -0.06
    POSITIVE LOGITS
    幹線
    0.07
    منی
    0.06
    President
    0.06
     roadway
    0.06
    acomment
    0.06
     пара
    0.06
    /List
    0.06
     حرفه
    0.06
     mundane
    0.06
    上海
    0.06
    Act Density 0.037%

    No Known Activations