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

    Neuronpedia

    INDEX
    Explanations

    discussing features or concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Maori
    0.45
    aholic
    0.45
     stb
    0.44
     Georgia
    0.43
     Entrepreneur
    0.42
     entrepreneur
    0.42
     Metabolic
    0.42
     fructose
    0.41
     Dreaming
    0.41
     impos
    0.41
    POSITIVE LOGITS
    两个
    0.48
    \|,
    0.48
    راج
    0.47
     captions
    0.47
    。『
    0.47
    Რ
    0.46
    <<"
    0.45
    र्भ
    0.45
    سوال
    0.45
    ကျွန်
    0.45
    Act Density 0.004%

    No Known Activations