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

    Neuronpedia

    INDEX
    Explanations

    math, equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sobre
    -0.07
     회
    -0.07
     halftime
    -0.07
     корот
    -0.07
    ानद
    -0.06
     einmal
    -0.06
    charAt
    -0.06
    bservice
    -0.06
     المع
    -0.06
     RuntimeException
    -0.06
    POSITIVE LOGITS
     ding
    0.06
     valued
    0.06
     W
    0.06
    depth
    0.06
     groom
    0.06
     Impro
    0.06
     wished
    0.06
     ned
    0.06
    ))/(
    0.06
     Caps
    0.06
    Act Density 0.008%

    No Known Activations