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

    Neuronpedia

    INDEX
    Explanations

    discover, generate, or translate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    CB
    0.44
     cotton
    0.43
    極
    0.43
    3
    0.41
     polarity
    0.41
    Polar
    0.41
     continuous
    0.40
    Cotton
    0.40
    polarity
    0.39
    Anh
    0.39
    POSITIVE LOGITS
     Leistungen
    0.44
    庣
    0.44
     दू
    0.42
     exer
    0.42
     Gén
    0.42
    ပြင်
    0.41
     dejó
    0.41
     adiab
    0.41
     familiares
    0.41
     DNIs
    0.41
    Act Density 0.003%

    No Known Activations