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

    Neuronpedia

    INDEX
    Explanations

    keywords `user`, `self`, `def` and `global` in Python code

    oai_token-act-pair · gemini-2.0-flash

    def

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     оригіналу
    -0.65
     تانيه
    -0.65
    BagConstraints
    -0.64
     Inscrivez
    -0.61
     Connectez
    -0.59
     insuffisamment
    -0.59
     Palt
    -0.59
    ReusableCell
    -0.58
    IVersion
    -0.57
     generalised
    -0.57
    POSITIVE LOGITS
    <bos>
    1.05
    "
    0.52
    ">//
    0.46
    Vidite
    0.44
    aarrggbb
    0.44
    ".
    0.44
    @
    0.44
        
    0.43
    ”
    0.42
    ."
    0.42
    Act Density 6.323%

    No Known Activations