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

    Neuronpedia

    INDEX
    Explanations

    git merge conflicts and commits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    あります
    1.14
     lebih
    1.13
    jähr
    1.10
    ের
    1.10
    ে
    1.09
    kül
    1.09
    yaratan
    1.08
    ρισ
    1.08
    Morning
    1.08
    ెస్
    1.06
    POSITIVE LOGITS
    율
    1.23
     sociali
    1.20
     viajes
    1.19
     hospitable
    1.18
    𝓈
    1.17
    辿
    1.17
     Melon
    1.16
     biota
    1.16
     desee
    1.16
     мы
    1.15
    Act Density 0.000%

    No Known Activations