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

    Neuronpedia

    INDEX
    Explanations

    state of being, or association

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    а
    0.90
    го
    0.89
    дно
    0.86
    в
    0.84
    m
    0.82
     а
    0.80
    an
    0.79
    🠀
    0.77
    ترام
    0.77
    尔
    0.77
    POSITIVE LOGITS
    োগ্রাফ
    0.95
     defocused
    0.91
    われ
    0.88
     sightings
    0.88
    ﮯ
    0.87
     fibrils
    0.85
    0.85
     embryos
    0.84
     лигасы
    0.83
    ির
    0.82
    Act Density 0.221%

    No Known Activations