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

    Neuronpedia

    INDEX
    Explanations

    interviews, reviews

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    BTC
    -0.07
    _LANG
    -0.07
    [random
    -0.07
    رم
    -0.07
    -valid
    -0.07
     bottoms
    -0.06
     AppleWebKit
    -0.06
    結果
    -0.06
    .place
    -0.06
    À
    -0.06
    POSITIVE LOGITS
    voke
    0.06
    =[]↵
    0.06
     São
    0.06
     Ukrainian
    0.06
    OCUMENT
    0.06
     McKay
    0.06
     Quantum
    0.06
    essional
    0.06
     budou
    0.06
     beyond
    0.06
    Act Density 0.015%

    No Known Activations