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

    Neuronpedia

    INDEX
    Explanations

    Economic, new, image

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    人
    0.66
    antaranya
    0.62
    ี้
    0.62
    .'),
    0.60
    .​​
    0.59
    .
    0.59
    az
    0.58
    נה
    0.56
    ها
    0.56
    ne
    0.55
    POSITIVE LOGITS
    ገልግሎ
    0.56
     This
    0.54
    el
    0.54
     The
    0.54
     sınır
    0.51
     ABS
    0.50
     الا
    0.50
     नया
    0.50
    ،
    0.49
     dogged
    0.49
    Act Density 0.206%

    No Known Activations