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

    Neuronpedia

    INDEX
    Explanations

    mathematical proofs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Exclude
    -0.09
     tents
    -0.08
     ನೆರ
    -0.08
     gegense
    -0.07
     रंग
    -0.07
     взаим
    -0.07
     exclusions
    -0.07
     дым
    -0.07
     Tent
    -0.07
    筛
    -0.07
    POSITIVE LOGITS
     části
    0.10
     plateau
    0.09
    асти
    0.08
     chopped
    0.08
     તેનું
    0.08
     decreasing
    0.08
     decreases
    0.08
    跌
    0.08
     saddened
    0.08
     chops
    0.08
    Act Density 0.032%

    No Known Activations