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

    Neuronpedia

    INDEX
    Explanations

    “ These

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Enhancement
    1.52
     Feature
    1.47
     Mania
    1.46
     Deviation
    1.45
     Biodiversity
    1.44
     Tool
    1.44
     Dividend
    1.44
     Departure
    1.43
     Conditioner
    1.41
     Impact
    1.40
    POSITIVE LOGITS
    the
    2.20
    there
    2.00
    this
    1.94
    they
    1.90
    these
    1.73
    we
    1.72
    when
    1.70
    you
    1.68
    their
    1.67
    despite
    1.66
    Act Density 0.383%

    No Known Activations