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

    Neuronpedia

    INDEX
    Explanations

    code syntax elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Mahon
    0.38
    Roasted
    0.35
     tannins
    0.34
     glands
    0.34
    Henderson
    0.34
     phenolic
    0.34
    Robinson
    0.34
    Mountains
    0.33
    Essentially
    0.33
    Prairie
    0.33
    POSITIVE LOGITS
    ::
    0.39
     +=
    0.34
    argv
    0.33
     argv
    0.33
     );
    0.33
     />
    0.33
     std
    0.33
     '';
    0.32
     initialize
    0.32
     ustaw
    0.32
    Act Density 0.021%

    No Known Activations