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

    Neuronpedia

    INDEX
    Explanations

    here

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     protr
    -0.08
    _dimensions
    -0.08
    发布日期
    -0.08
    _seconds
    -0.08
     watching
    -0.08
    atsis
    -0.07
    getting
    -0.07
    _learning
    -0.07
    ýan
    -0.07
    learning
    -0.07
    POSITIVE LOGITS
    Spreadsheet
    0.09
    риз
    0.08
     compiled
    0.08
     чек
    0.07
     erre
    0.07
     succ
    0.07
     явно
    0.07
    त्र
    0.07
    eft
    0.07
     स्पष्ट
    0.07
    Act Density 0.004%

    No Known Activations