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

    Neuronpedia

    INDEX
    Explanations

    cultural and ethical concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Архівовано
    0.42
     તપાસ
    0.41
    гласно
    0.38
     Fär
    0.38
     samt
    0.37
    ionato
    0.37
     hiked
    0.37
     deemed
    0.36
     Apex
    0.36
     میز
    0.36
    POSITIVE LOGITS
    ULTURAL
    0.47
    TL
    0.44
    OPEN
    0.40
    ULD
    0.39
    ekyll
    0.39
    ultural
    0.39
    ച്ച
    0.38
    ULTURE
    0.38
     ಘ
    0.37
    オ
    0.36
    Act Density 0.000%

    No Known Activations