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

    Neuronpedia

    INDEX
    Explanations

    numerical calculations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     transitions
    -0.09
     тро
    -0.08
     integrity
    -0.08
     modifies
    -0.08
    Transition
    -0.07
    Disabled
    -0.07
    dam
    -0.07
     мах
    -0.07
     пал
    -0.07
    transition
    -0.07
    POSITIVE LOGITS
     mjesta
    0.09
    ِي
    0.09
     dramatically
    0.09
     República
    0.09
     drastically
    0.09
    াত
    0.08
     (!)
    0.08
    !</
    0.08
    ต่ำ
    0.08
     pantalon
    0.08
    Act Density 0.181%

    No Known Activations