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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    *))
    -0.07
     Brushes
    -0.07
    <W
    -0.07
     золот
    -0.07
     ISC
    -0.06
    :p
    -0.06
     acceleration
    -0.06
    -labelledby
    -0.06
    _MINUS
    -0.06
     расч
    -0.06
    POSITIVE LOGITS
     Moss
    0.07
     Kits
    0.06
     Flex
    0.06
     PARK
    0.06
    SMS
    0.06
     tirelessly
    0.06
     Mitt
    0.06
     popular
    0.06
    _business
    0.06
    사의
    0.06
    Act Density 0.007%

    No Known Activations