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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Square
    -0.07
     古
    -0.07
    quite
    -0.07
     Sites
    -0.06
     zombie
    -0.06
    izoph
    -0.06
    958
    -0.06
     브라
    -0.06
    Pattern
    -0.06
     ท
    -0.06
    POSITIVE LOGITS
    (option
    0.06
     происходит
    0.06
    productId
    0.06
    AYER
    0.06
    сию
    0.06
     zajist
    0.06
    違
    0.06
    :%
    0.06
    transparent
    0.06
    _PLATFORM
    0.06
    Act Density 0.008%

    No Known Activations