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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and symbols related to functions and variables

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Mathematical notation and symbols

    np_acts-logits-general · gemini-2.0-flash

    mathematical expressions with `mathbb`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Cardigan
    -0.62
    utilisons
    -0.62
     Moran
    -0.60
     Canyon
    -0.59
     NAC
    -0.57
     Vang
    -0.57
    NAC
    -0.56
     Gleason
    -0.55
    Canyon
    -0.54
     Fry
    -0.54
    POSITIVE LOGITS
     Bolton
    0.86
     Belmont
    0.81
     Dunlop
    0.80
     Dunne
    0.78
     Berne
    0.75
     Vau
    0.74
     Bern
    0.73
    slidesPer
    0.70
     Chappell
    0.69
     Chau
    0.67
    Act Density 0.682%

    No Known Activations