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

    Neuronpedia

    INDEX
    Explanations

    article

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    song
    -0.07
    (normal
    -0.07
    amide
    -0.07
    .UInt
    -0.06
    USTER
    -0.06
    seven
    -0.06
    /update
    -0.06
     Hyper
    -0.06
    hyp
    -0.06
     oby
    -0.06
    POSITIVE LOGITS
    memset
    0.07
    特色
    0.07
     pnl
    0.06
     memnun
    0.06
    |wx
    0.06
    .repaint
    0.06
    anut
    0.06
     kanı
    0.06
     해외
    0.06
    Năm
    0.06
    Act Density 0.011%

    No Known Activations