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

    Neuronpedia

    INDEX
    Explanations

    percentages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     stupidity
    -0.07
    ‡
    -0.07
    annie
    -0.06
     sqlite
    -0.06
    ํ
    -0.06
    _formatter
    -0.06
    專
    -0.06
     spoil
    -0.06
     ridden
    -0.06
     juven
    -0.06
    POSITIVE LOGITS
     membranes
    0.06
     в
    0.06
     midfield
    0.06
     V
    0.06
    Ad
    0.06
    .Setter
    0.06
     admitting
    0.06
     saison
    0.06
    BUM
    0.06
    ilecek
    0.06
    Act Density 0.124%

    No Known Activations