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

    Neuronpedia

    INDEX
    Explanations

    URLs and references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     entry
    0.22
     SL
    0.21
    entry
    0.20
    ‟
    0.19
     for
    0.19
     nomenclature
    0.18
     non
    0.18
     numbering
    0.18
    пециа
    0.18
     approved
    0.18
    POSITIVE LOGITS
    tır
    0.22
     శక్తి
    0.22
     เมตร
    0.22
    Ꮬ
    0.22
    ๎
    0.21
    𝓪
    0.21
    汽车
    0.21
    ško
    0.21
    狮
    0.21
     خرید
    0.20
    Act Density 0.091%

    No Known Activations