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

    Neuronpedia

    INDEX
    Explanations

    lists with context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Writ
    0.42
     computadora
    0.38
     MPEG
    0.37
     komputer
    0.36
     xmas
    0.36
     aperta
    0.36
     christmas
    0.36
     ekran
    0.35
     customised
    0.35
     ordinateur
    0.35
    POSITIVE LOGITS
    capitalize
    0.42
     ***
    0.42
    igos
    0.40
     लीग
    0.40
    นิยม
    0.39
    利
    0.39
    ନା
    0.39
     Sự
    0.37
     ನಿಮ್ಮ
    0.37
    ***
    0.37
    Act Density 0.001%

    No Known Activations