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

    Neuronpedia

    INDEX
    Explanations

    python script execution block

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    APAN
    0.44
     আসিয়
    0.42
    Inte
    0.39
    পর্ব
    0.38
     demok
    0.38
    Bathroom
    0.37
    SPR
    0.37
    Dinner
    0.37
    쑤
    0.37
     демокра
    0.36
    POSITIVE LOGITS
     -----
    0.72
     ---
    0.71
     ___
    0.71
     ----
    0.70
     ------
    0.68
     ____
    0.64
     _____
    0.63
     ______
    0.63
     _______
    0.62
     -------
    0.61
    Act Density 0.000%

    No Known Activations