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

    Neuronpedia

    INDEX
    Explanations

    function calls and data structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ...");
    0.64
    "});
    0.62
     "));
    0.59
    !"));
    0.59
    "]);
    0.58
    "));
    0.57
    ...";
    0.56
     ...");
    0.56
    !");
    0.56
    "};
    0.55
    POSITIVE LOGITS
    kwargs
    0.82
    fetchone
    0.78
    wsgi
    0.78
    ([(
    0.75
    dtype
    0.75
    elif
    0.74
    (**
    0.74
    fetchall
    0.73
    ({'
    0.72
    __(
    0.72
    Act Density 0.756%

    No Known Activations