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

    Neuronpedia

    INDEX
    Explanations

    Ö and similar characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     words
    0.46
    φων
    0.45
    zeros
    0.41
     fora
    0.41
     coraz
    0.40
    words
    0.40
     zeros
    0.38
    軚
    0.38
     numbered
    0.38
     поду
    0.38
    POSITIVE LOGITS
    टक
    0.40
    ürü
    0.40
    捅
    0.40
    nti
    0.39
     افر
    0.39
    쌓
    0.38
     Suggestions
    0.38
    一身
    0.38
    특히
    0.37
    ティック
    0.37
    Act Density 0.002%

    No Known Activations