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

    Neuronpedia

    INDEX
    Explanations

    lists and commas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Thanh
    -0.07
    _pose
    -0.07
     taxi
    -0.06
    个人
    -0.06
    SMS
    -0.06
    _tags
    -0.06
     Buddha
    -0.06
    빙
    -0.06
     peasant
    -0.06
    aje
    -0.06
    POSITIVE LOGITS
    ѕ
    0.07
    aryana
    0.07
     Stam
    0.06
    Copying
    0.06
    (fc
    0.06
    refixer
    0.06
    getCell
    0.06
     incons
    0.06
     DataContext
    0.06
    /")↵
    0.05
    Act Density 0.043%

    No Known Activations