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

    Neuronpedia

    INDEX
    Explanations

    B or 2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    :ss
    -0.07
    _FLAGS
    -0.06
    Fr
    -0.06
    anlar
    -0.06
     accommodations
    -0.06
     Midlands
    -0.06
     weighs
    -0.06
     <>
    -0.06
    [o
    -0.06
     FAR
    -0.06
    POSITIVE LOGITS
    식
    0.07
     CPI
    0.07
    crud
    0.07
    《
    0.07
    <Text
    0.06
    ＆
    0.06
    λού
    0.06
     Голов
    0.06
     lad
    0.06
    炉
    0.06
    Act Density 0.033%

    No Known Activations