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

    Neuronpedia

    INDEX
    Explanations

    semicolons in code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    раз
    0.45
    現在は
    0.42
     nesta
    0.42
    ในปี
    0.40
    近日
    0.40
    Destination
    0.39
    Recently
    0.39
    民國
    0.39
     ১৯৪৭
    0.39
    artikel
    0.38
    POSITIVE LOGITS
    {(\
    0.40
     subsonic
    0.38
    ීය
    0.38
     triggered
    0.38
     automata
    0.38
    이어
    0.36
     ফিরিয়ে
    0.36
     amenable
    0.36
     }{
    0.35
     juste
    0.35
    Act Density 0.002%

    No Known Activations