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

    Neuronpedia

    INDEX
    Explanations

    parentheses, comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ерта
    -0.07
    pre
    -0.07
     dn
    -0.07
     качестве
    -0.06
     тим
    -0.06
    words
    -0.06
     وأ
    -0.06
    納
    -0.06
    ีด
    -0.06
    де
    -0.06
    POSITIVE LOGITS
    stuff
    0.06
    .ActionEvent
    0.06
     béné
    0.06
    'name
    0.06
    <Path
    0.06
    _DIG
    0.06
    witter
    0.06
    358
    0.06
    ’on
    0.06
    Fact
    0.06
    Act Density 0.004%

    No Known Activations