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

    Neuronpedia

    INDEX
    Explanations

    website setup and traffic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    The
    0.45
     The
    0.41
    LD
    0.40
    з
    0.39
    ਯ
    0.39
    J
    0.39
    tl
    0.38
    L
    0.38
    ೆ
    0.38
    leurs
    0.38
    POSITIVE LOGITS
     үшін
    0.54
    按钮
    0.51
    בין
    0.51
    сів
    0.49
     בין
    0.48
     pagal
    0.48
    utcnow
    0.47
    ذی
    0.47
     ahorita
    0.47
    ٹین
    0.47
    Act Density 0.001%

    No Known Activations