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

    Neuronpedia

    INDEX
    Explanations

    reading important disclaimers before posts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ка
    1.35
    ر
    1.34
    ר
    1.34
    า
    1.26
    lø
    1.24
    are
    1.22
    र
    1.19
    ர்
    1.15
    ן
    1.14
    at
    1.13
    POSITIVE LOGITS
     Elovl
    1.18
     yerden
    1.11
     ponctués
    1.05
     bouts
    1.05
    ص
    1.05
     residuals
    1.04
    用了
    1.03
     headwinds
    1.01
    懑
    0.99
     posticis
    0.99
    Act Density 0.090%

    No Known Activations