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

    Neuronpedia

    INDEX
    Explanations

    survive

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    wrong
    -0.07
    ерта
    -0.07
    (static
    -0.07
    _rat
    -0.06
    bage
    -0.06
    чих
    -0.06
     مستقیم
    -0.06
     hơn
    -0.06
     относ
    -0.06
     Externí
    -0.06
    POSITIVE LOGITS
    597
    0.07
    .Collapsed
    0.07
     Appliances
    0.06
    CRC
    0.06
     composite
    0.06
     Tube
    0.06
     Seah
    0.06
    ometer
    0.06
     poles
    0.06
    489
    0.06
    Act Density 0.020%

    No Known Activations