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

    Neuronpedia

    INDEX
    Explanations

    all the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dowol
    0.23
    兘
    0.21
     البعض
    0.21
    ಾದರೂ
    0.20
    ujesz
    0.20
     किस्मत
    0.20
     რომლებიც
    0.20
    *,
    0.20
     Along
    0.19
     Embora
    0.19
    POSITIVE LOGITS
     the
    0.33
     that
    0.28
     its
    0.28
    ните
    0.27
     accomp
    0.26
     dei
    0.25
    的的
    0.25
     അതിന്റെ
    0.25
     everything
    0.23
    вите
    0.23
    Act Density 0.014%

    No Known Activations