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

    Neuronpedia

    INDEX
    Explanations

    learning from data and rules

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     மந்திர
    0.45
    windowActionBar
    0.45
    DanhMuc
    0.44
     ಆತ್ಮ
    0.44
    旨
    0.41
     ଦ
    0.41
    LeftSide
    0.41
    fica
    0.40
    िरिक्स
    0.39
    勃
    0.39
    POSITIVE LOGITS
     Học
    0.47
     обучения
    0.46
    We
    0.45
     Voyage
    0.42
    สอน
    0.41
     och
    0.41
     dokument
    0.41
    रोवर
    0.41
     appren
    0.41
     সড়
    0.40
    Act Density 0.011%

    No Known Activations