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

    Neuronpedia

    INDEX
    Explanations

    function arguments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     letting
    0.71
     hi
    0.67
     web
    0.67
     g
    0.66
     let
    0.64
     mal
    0.64
     wrist
    0.64
     Let
    0.63
     stone
    0.62
     tym
    0.60
    POSITIVE LOGITS
    Args
    1.19
    Parameters
    1.06
    Keywords
    0.92
    Conclusion
    0.90
    Keyword
    0.88
     Keywords
    0.86
    Arguments
    0.85
     Args
    0.85
    ।--
    0.82
     conclusione
    0.81
    Act Density 0.071%

    No Known Activations