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

    Neuronpedia

    INDEX
    Explanations

    format and layout specifications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    1.50
     $
    1.27
     to
    1.19
     or
    1.15
     but
    1.14
     in
    1.12
    1
    1.06
     is
    1.04
    2
    1.01
    v
    1.00
    POSITIVE LOGITS
    myButtons
    1.23
     Feuilles
    1.13
    стика
    1.11
     Conseils
    1.09
    ０
    1.09
     tumeurs
    1.07
     Sélection
    1.07
     emphas
    1.06
     duckys
    1.06
     Antennes
    1.05
    Act Density 0.465%

    No Known Activations