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

    Neuronpedia

    INDEX
    Explanations

    the whole scope

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     느낌
    0.43
     نہیں۔
    0.41
    atorul
    0.41
     Pologne
    0.40
     almighty
    0.39
    KeyState
    0.39
     origem
    0.38
     اتفاق
    0.38
    GameState
    0.38
    enez
    0.37
    POSITIVE LOGITS
     entire
    0.95
     entirety
    0.86
    entire
    0.82
     gesamten
    0.79
     Entire
    0.69
    整个
    0.69
    Entire
    0.67
    整個
    0.66
     முழுவதும்
    0.66
     gesamte
    0.64
    Act Density 0.011%

    No Known Activations