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

    Neuronpedia

    INDEX
    Explanations

    enumerated lists

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     так
    -0.06
     than
    -0.06
     improvement
    -0.06
    рами
    -0.06
     widened
    -0.06
     labore
    -0.06
     indir
    -0.06
    μήμα
    -0.06
     حذف
    -0.05
    ικού
    -0.05
    POSITIVE LOGITS
     Sterling
    0.07
    \Catalog
    0.07
     Realt
    0.07
     диаг
    0.07
    ogue
    0.07
    _beam
    0.07
    (--
    0.06
    ベル
    0.06
     pinnacle
    0.06
    .Drop
    0.06
    Act Density 0.003%

    No Known Activations