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

    Neuronpedia

    INDEX
    Explanations

    python code like the definition of a class

    oai_token-act-pair · gemini-2.0-flash

    def

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     myſelf
    -1.04
     ―――――
    -0.96
     itſelf
    -0.96
     Majefty
    -0.94
     purpoſe
    -0.93
     Anſ
    -0.87
     ſtate
    -0.87
     étoit
    -0.87
     Eſ
    -0.85
     himſelf
    -0.84
    POSITIVE LOGITS
    DoubleQuotes
    0.82
    matchCondition
    0.81
    omitempty
    0.78
    <eos>
    0.78
    function
    0.77
    __((
    0.75
    ↵↵
    0.74
     function
    0.73
    func
    0.67
    __':
    0.66
    Act Density 0.222%

    No Known Activations