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

    Neuronpedia

    INDEX
    Explanations

    tell me

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     harmon
    0.39
    uminação
    0.38
    íoch
    0.36
     दिव्य
    0.36
    èvres
    0.36
    icillium
    0.35
     fle
    0.35
    нуться
    0.34
    شارة
    0.34
     esfuerzos
    0.34
    POSITIVE LOGITS
     tell
    0.70
     tells
    0.68
     tale
    0.66
     Tells
    0.64
     told
    0.63
    tale
    0.63
     Tell
    0.63
    Tell
    0.63
     tales
    0.62
    告诉
    0.60
    Act Density 0.023%

    No Known Activations