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

    Neuronpedia

    INDEX
    Explanations

    journal abbreviations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    밪
    -0.07
    (annotation
    -0.07
     Aur
    -0.07
     politique
    -0.06
    รวบ
    -0.06
    -driving
    -0.06
    𝖔
    -0.06
    /r
    -0.06
    ถนน
    -0.06
    (TestCase
    -0.06
    POSITIVE LOGITS
     certs
    0.07
    аж
    0.06
     utilizar
    0.06
    ن
    0.06
     Ames
    0.06
    Bits
    0.06
     glare
    0.06
     houses
    0.06
    fits
    0.06
    Param
    0.06
    Act Density 0.005%

    No Known Activations