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

    Neuronpedia

    INDEX
    Explanations

    your name and address

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     confir
    0.39
    truth
    0.38
     conceivably
    0.37
     lov
    0.37
     confirms
    0.37
     cakkh
    0.37
     haq
    0.37
    确认
    0.36
     actuality
    0.36
    detail
    0.35
    POSITIVE LOGITS
     πα
    0.39
     OUR
    0.38
     pune
    0.38
    pause
    0.36
     Our
    0.36
     STREET
    0.36
     ../
    0.36
    Tab
    0.35
     Pause
    0.35
    Our
    0.35
    Act Density 0.002%

    No Known Activations