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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     “…
    -0.07
    [cell
    -0.07
     tele
    -0.06
     objs
    -0.06
    ढ
    -0.06
     Ά
    -0.06
    UniformLocation
    -0.06
    [*
    -0.06
     관리
    -0.06
    [test
    -0.06
    POSITIVE LOGITS
    loha
    0.06
     avant
    0.06
    ACCEPT
    0.06
     arranged
    0.06
     các
    0.06
    -packed
    0.06
     боя
    0.06
    require
    0.06
     Donation
    0.06
    articles
    0.06
    Act Density 0.042%

    No Known Activations