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

    Neuronpedia

    INDEX
    Explanations

    cast

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Podle
    -0.07
    ,function
    -0.07
     snippet
    -0.07
    系统
    -0.07
     Superior
    -0.06
     pero
    -0.06
    variables
    -0.06
     memorandum
    -0.06
     nghiên
    -0.06
     dazu
    -0.06
    POSITIVE LOGITS
     casting
    0.11
     Cast
    0.10
     cast
    0.10
    casting
    0.10
     Casting
    0.09
    Cast
    0.09
     Castro
    0.08
    cast
    0.08
    aycast
    0.08
    .Cast
    0.07
    Act Density 0.013%

    No Known Activations