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

    Neuronpedia

    INDEX
    Explanations

    function calls and method invocations in code

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

    code with angle brackets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AXB
    -0.60
    llac
    -0.59
     Auburn
    -0.57
    Auburn
    -0.57
    Pierce
    -0.56
    NEP
    -0.56
    UPAC
    -0.55
    tellar
    -0.55
     ſch
    -0.54
    Tach
    -0.54
    POSITIVE LOGITS
    >();
    1.84
    >();
    1.45
    >>();
    1.13
    <>();
    1.10
    >());
    1.09
    >()
    0.94
    <>();
    0.83
    >())
    0.82
    "]();
    0.80
    ]();
    0.80
    Act Density 0.002%

    No Known Activations