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

    Neuronpedia

    INDEX
    Explanations

    starting point

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ę
    0.47
     verschill
    0.43
    än
    0.42
    ö
    0.42
    ingen
    0.40
    utom
    0.40
    ımı
    0.39
    stances
    0.39
    ido
    0.37
    imi
    0.37
    POSITIVE LOGITS
    ა
    0.64
    т
    0.52
    ت
    0.51
    τούν
    0.50
    لای
    0.47
    ل
    0.47
     for
    0.46
    ަލ
    0.46
     মুক্তিফৌজ
    0.46
     anglers
    0.45
    Act Density 0.471%

    No Known Activations