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

    Neuronpedia

    INDEX
    Explanations

    checks for empty

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     وعلى
    1.27
     basados
    1.21
     ومع
    1.20
    اً
    1.19
    2
    1.19
    it
    1.17
    ρα
    1.15
     следу
    1.15
     aperto
    1.15
    ен
    1.13
    POSITIVE LOGITS
    м
    1.70
    రుగులు
    1.38
    空的
    1.33
     antifreeze
    1.30
    𝘴
    1.30
    ंत
    1.28
    slideDuplicate
    1.27
    其
    1.27
     picturesque
    1.27
    グレ
    1.25
    Act Density 0.184%

    No Known Activations