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

    Neuronpedia

    INDEX
    Explanations

    names and titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vs
    0.62
     |
    0.56
    -
    0.55
     #
    0.54
     _
    0.53
     *
    0.53
     //
    0.52
     –
    0.52
     factored
    0.52
     (
    0.51
    POSITIVE LOGITS
     Stewart
    0.97
     Tracey
    0.96
     McLaren
    0.95
     Harris
    0.92
     Hodgson
    0.91
     McKenzie
    0.91
     Saunders
    0.90
    Harris
    0.90
    Stewart
    0.90
    <unused1095>
    0.89
    Act Density 0.014%

    No Known Activations