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

    Neuronpedia

    INDEX
    Explanations

    word variations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     five
    0.92
     multiple
    0.91
     three
    0.88
     no
    0.88
     g
    0.87
     or
    0.85
     a
    0.85
     large
    0.83
     e
    0.83
     non
    0.82
    POSITIVE LOGITS
     CCSDT
    0.95
     Förderung
    0.94
    Barrier
    0.94
    филлер
    0.87
    Prz
    0.87
    Situ
    0.86
    Gamepad
    0.86
    வலி
    0.85
    發展
    0.83
    Investment
    0.83
    Act Density 0.011%

    No Known Activations