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

    Neuronpedia

    INDEX
    Explanations

    Data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     modem
    -0.07
    .observe
    -0.07
     ^^
    -0.06
     мину
    -0.06
     april
    -0.06
    _FC
    -0.06
    ći
    -0.06
     روابط
    -0.06
    ком
    -0.06
    Me
    -0.06
    POSITIVE LOGITS
     Data
    0.07
    .categories
    0.07
    moves
    0.07
    outcome
    0.07
     طبي
    0.07
    departureday
    0.06
     performan
    0.06
    Performance
    0.06
     creampie
    0.06
    data
    0.06
    Act Density 0.023%

    No Known Activations