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

    Neuronpedia

    INDEX
    Explanations

    showing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    owing
    -0.09
     bildet
    -0.09
    acol
    -0.08
    おります
    -0.08
     verk
    -0.08
     upbeat
    -0.08
    readcrumb
    -0.08
     bilden
    -0.08
    yta
    -0.07
    ull
    -0.07
    POSITIVE LOGITS
     flexibility
    0.09
     adanya
    0.09
     versatility
    0.09
     perseverance
    0.08
    光
    0.08
     underscores
    0.08
     veelzijd
    0.08
     انتظار
    0.07
     фен
    0.07
     testament
    0.07
    Act Density 0.075%

    No Known Activations