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

    Neuronpedia

    INDEX
    Explanations

    Computer languages and networking

    np_max-act · gemini-2.0-flash

    The neuron activates on descriptive adjectives that characterize Python’s language features (e.g. interpreted, object-oriented, high-level, dynamic).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    abilia
    -0.07
    英語
    -0.07
     Greeks
    -0.07
     churches
    -0.07
    opens
    -0.07
    Hard
    -0.07
    par
    -0.06
     Leben
    -0.06
    Disc
    -0.06
    eker
    -0.06
    POSITIVE LOGITS
    _process
    0.07
     CONTEXT
    0.06
     мист
    0.06
    (wx
    0.06
     Khoa
    0.06
     Cannot
    0.06
    Dispatcher
    0.06
     �
    0.06
    759
    0.06
    mol
    0.06
    Act Density 0.029%

    No Known Activations