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

    Neuronpedia

    INDEX
    Explanations

    connecting phrases with follow-up words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝘵
    1.31
    ר
    1.27
     agreements
    1.23
    1.17
    𝘢
    1.16
    пля
    1.11
     eruptions
    1.11
    냉
    1.09
    1.08
    ित
    1.08
    POSITIVE LOGITS
    昰
    1.19
    ا
    1.15
     cleans
    1.10
    amt
    1.10
     zeich
    1.10
    стары
    1.10
    ಕಾಶ
    1.09
     sortie
    1.09
     怪
    1.09
    ="$
    1.09
    Act Density 0.000%

    No Known Activations