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

    Neuronpedia

    INDEX
    Explanations

    occurrences of double underscores, which often indicate special methods or attributes in programming contexts

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

    Python `__` constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    土
    -0.41
     Telerik
    -0.40
    FirebaseDatabase
    -0.39
    Kn
    -0.36
    δος
    -0.36
     Gayle
    -0.36
     Kn
    -0.36
    eqref
    -0.35
     Jody
    -0.35
     Palgrave
    -0.34
    POSITIVE LOGITS
    __.
    2.55
    __,
    1.31
    __;
    0.96
    __:
    0.94
    __["
    0.94
    __[
    0.89
     nakalista
    0.86
    __/
    0.79
    __)
    0.77
    __).
    0.73
    Act Density 0.004%

    No Known Activations