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

    Neuronpedia

    INDEX
    Explanations

    specific examples of categories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ινων
    0.41
     अथवा
    0.40
    )_{
    0.39
    ／
    0.39
    |_{\
    0.38
    ку
    0.38
    第八
    0.37
     vegetarians
    0.37
    (@"
    0.37
    ঙ্গা
    0.37
    POSITIVE LOGITS
    尤其是
    0.60
    特别是
    0.55
     मसलन
    0.51
     včetně
    0.49
     особенно
    0.48
     включая
    0.48
     incluindo
    0.48
     terutama
    0.47
     특히
    0.46
    namely
    0.46
    Act Density 0.243%

    No Known Activations