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

    Neuronpedia

    INDEX
    Explanations

    computer code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     competed
    -0.07
     tint
    -0.07
     ><
    -0.07
    ئ
    -0.07
     foc
    -0.07
    竞争优势
    -0.07
    oment
    -0.07
    ⵢ
    -0.06
     tack
    -0.06
    .onclick
    -0.06
    POSITIVE LOGITS
     Shadows
    0.07
     constants
    0.07
    rolling
    0.07
    장
    0.07
     summarizes
    0.07
     регистра
    0.07
     über
    0.07
    ypass
    0.07
    iframe
    0.07
     planes
    0.07
    Act Density 0.261%

    No Known Activations