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

    Neuronpedia

    INDEX
    Explanations

    DISPOSE, EXIT_ON_CLOSE, ERRMODE

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    fifty
    0.42
    фт
    0.41
    Twelve
    0.40
    Eleven
    0.40
     fifties
    0.39
     sixties
    0.39
     Envi
    0.39
    Flags
    0.38
     nineties
    0.38
    㭂
    0.38
    POSITIVE LOGITS
    othy
    0.42
    yek
    0.41
    Зак
    0.41
     Зак
    0.40
    YES
    0.38
    ⁄
    0.38
     fermé
    0.37
    केंद्र
    0.37
    ικής
    0.37
     PLANE
    0.37
    Act Density 0.002%

    No Known Activations