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

    Neuronpedia

    INDEX
    Explanations

    classmethod

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uvwxyz
    -0.07
    _sl
    -0.06
     Dining
    -0.06
     offences
    -0.06
    関係
    -0.06
    -Line
    -0.06
    Statement
    -0.06
    'im
    -0.06
    ATABASE
    -0.06
    ’de
    -0.06
    POSITIVE LOGITS
    LEncoder
    0.07
    apeake
    0.07
     біля
    0.07
    λμ
    0.07
    reating
    0.06
    溫
    0.06
     пож
    0.06
     української
    0.06
     留
    0.06
    训
    0.06
    Act Density 0.002%

    No Known Activations