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

    Neuronpedia

    INDEX
    Explanations

    explanation why

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ^^
    0.99
    .`);
    0.95
     **,
    0.95
     (),
    0.94
    ))\
    0.90
     ();
    0.90
     ...");
    0.90
    ...\
    0.88
     {});
    0.87
     {};
    0.85
    POSITIVE LOGITS
    How
    1.20
    Why
    1.16
     How
    1.08
    What
    1.05
     Why
    0.99
    Important
    0.93
     What
    0.90
    how
    0.90
    why
    0.89
    Examples
    0.86
    Act Density 0.202%

    No Known Activations