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

    Neuronpedia

    INDEX
    Explanations

    comment markers //

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Using
    1.02
     Rather
    0.92
     Firm
    0.92
     Within
    0.91
     Relatively
    0.90
     Almost
    0.87
     Instead
    0.87
     Endless
    0.85
     Establishing
    0.84
     Learning
    0.83
    POSITIVE LOGITS
    #
    1.23
    //
    1.14
    @
    0.99
    ;
    0.96
    \
    0.94
    [
    0.93
    .
    0.91
    |
    0.91
    )
    0.90
    +
    0.90
    Act Density 0.237%

    No Known Activations