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

    Neuronpedia

    INDEX
    Explanations

    programming-related keywords, particularly focusing on methods and decorators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    method

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    spotted
    -0.46
    EndContext
    -0.42
     '\\;'
    -0.41
    PostBack
    -0.38
     quint
    -0.38
     spotted
    -0.37
    existsSync
    -0.37
    presumably
    -0.36
    passage
    -0.36
    Spotted
    -0.36
    POSITIVE LOGITS
     method
    1.08
    method
    1.05
     Method
    0.98
    Method
    0.90
    METHOD
    0.86
     méthode
    0.85
     METHOD
    0.83
     método
    0.81
     Methode
    0.80
    methode
    0.79
    Act Density 0.001%

    No Known Activations