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

    Neuronpedia

    INDEX
    Explanations

    parentheses and curly brackets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -char
    -0.07
    terminate
    -0.07
    經
    -0.07
    ивання
    -0.06
     toughest
    -0.06
    摇
    -0.06
     المغ
    -0.06
    arry
    -0.06
    minimal
    -0.06
     तर
    -0.06
    POSITIVE LOGITS
     ویژگی
    0.07
    .http
    0.06
    Added
    0.06
     demanded
    0.06
    �
    0.06
    MENTS
    0.06
     Complete
    0.06
     되었다
    0.06
    lean
    0.06
    	Start
    0.06
    Act Density 0.013%

    No Known Activations