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

    Neuronpedia

    INDEX
    Explanations

    welcome to the world

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     जीके
    0.38
     seizoen
    0.38
    ঞ্জের
    0.37
     ovog
    0.37
    阙
    0.36
    пиа
    0.36
    山の
    0.36
    선의
    0.36
     هذا
    0.35
    пта
    0.35
    POSITIVE LOGITS
     outset
    0.41
     используя
    0.38
     addictions
    0.38
     joys
    0.38
     मुताब
    0.37
    beginning
    0.37
     begin
    0.37
     fray
    0.37
     beginning
    0.36
    Institute
    0.36
    Act Density 0.003%

    No Known Activations