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

    Neuronpedia

    INDEX
    Explanations

    examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     (
    1.59
     （
    1.38
     (_,
    1.33
     ('
    1.28
     (.)
    1.26
     ((
    1.21
     ([
    1.20
    (
    1.16
    （
    1.14
     (((
    1.13
    POSITIVE LOGITS
    ?).
    2.54
    which
    2.52
    ?),
    2.51
    including
    2.37
    !!)
    2.37
    although
    2.33
    usually
    2.32
    assuming
    2.27
    often
    2.24
    see
    2.23
    Act Density 0.881%

    No Known Activations