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

    Neuronpedia

    INDEX
    Explanations

    call for comments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     assassin
    -0.09
    rai
    -0.08
    rhein
    -0.08
    uit
    -0.08
    aughty
    -0.08
    rr
    -0.08
    Matchers
    -0.07
     cassette
    -0.07
    ometric
    -0.07
     Riley
    -0.07
    POSITIVE LOGITS
    ความคิดเห็น
    0.12
     의견
    0.12
    意见
    0.11
     مجتمع
    0.10
     forums
    0.10
     convid
    0.10
     пікір
    0.10
     фору
    0.10
     форум
    0.10
     encourages
    0.10
    Act Density 0.041%

    No Known Activations