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

    Neuronpedia

    INDEX
    Explanations

    News articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (products
    -0.07
     zih
    -0.07
     неиз
    -0.06
    쳤다
    -0.06
     marshal
    -0.06
    照片
    -0.06
     sonunda
    -0.06
    apikey
    -0.06
    foreach
    -0.06
     Dixon
    -0.06
    POSITIVE LOGITS
     challeng
    0.07
     вне
    0.07
    468
    0.06
     Caul
    0.06
     Мар
    0.06
     formato
    0.06
     esta
    0.06
    Idx
    0.06
    _Common
    0.06
     setDate
    0.06
    Act Density 0.164%

    No Known Activations