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

    Neuronpedia

    INDEX
    Explanations

    code function calls

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Measures
    -0.08
    kish
    -0.08
     grö
    -0.08
     INTRO
    -0.08
     trabaj
    -0.08
     rulers
    -0.08
    better
    -0.07
    ikle
    -0.07
     intro
    -0.07
     arbejder
    -0.07
    POSITIVE LOGITS
     arguments
    0.12
    .arguments
    0.12
    _args
    0.12
    Arguments
    0.11
    调用
    0.11
     Arguments
    0.11
    _ARGS
    0.11
    _arguments
    0.11
    arguments
    0.11
    $args
    0.11
    Act Density 0.016%

    No Known Activations