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

    Neuronpedia

    INDEX
    Explanations

    text following punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    The
    1.12
    Some
    1.04
    Most
    1.03
    Every
    0.99
    Several
    0.97
    Providing
    0.95
    Very
    0.95
    very
    0.95
     The
    0.95
     the
    0.92
    POSITIVE LOGITS
     reefs
    1.12
     artifacts
    1.04
     Dioxide
    1.03
     appliances
    1.01
     ailments
    1.00
     seams
    1.00
     polytopes
    0.97
     couches
    0.97
     landfills
    0.96
     matchups
    0.96
    Act Density 0.020%

    No Known Activations