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

    Neuronpedia

    INDEX
    Explanations

    end

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Stanford
    -0.07
     bilder
    -0.07
    _svg
    -0.07
     hvis
    -0.07
     ochran
    -0.07
    /screen
    -0.07
     aydın
    -0.06
     sugars
    -0.06
    盖
    -0.06
     prostě
    -0.06
    POSITIVE LOGITS
     thuật
    0.06
     mph
    0.06
     Analog
    0.06
    Ấ
    0.06
    ınız
    0.06
     val
    0.06
    ائر
    0.06
    ("."
    0.05
     locale
    0.05
    .so
    0.05
    Act Density 0.042%

    No Known Activations