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

    Neuronpedia

    INDEX
    Explanations

    Misspellings/Informal Language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     REST
    -0.08
     Army
    -0.07
    -more
    -0.07
     trou
    -0.07
    gui
    -0.06
     Та
    -0.06
    استان
    -0.06
     Pe
    -0.06
     analytical
    -0.06
    /A
    -0.06
    POSITIVE LOGITS
    ίνει
    0.07
     उठ
    0.06
    standen
    0.06
    .delta
    0.06
    Structured
    0.06
    شن
    0.06
     ніч
    0.06
    าศาสตร
    0.06
    ائي
    0.06
    ملة
    0.06
    Act Density 0.011%

    No Known Activations