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

    Neuronpedia

    INDEX
    Explanations

    circle

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Commission
    -0.09
    owe
    -0.07
    (engine
    -0.07
    研
    -0.07
     garantia
    -0.07
     garantía
    -0.07
     ημέ
    -0.07
     shaping
    -0.07
     Cogn
    -0.07
     தெ
    -0.07
    POSITIVE LOGITS
     вокруг
    0.09
    เกิด
    0.09
    भो
    0.08
     organisée
    0.08
    pic
    0.08
     ilgili
    0.08
     organisiert
    0.08
    icle
    0.08
     centered
    0.08
    დე
    0.08
    Act Density 0.008%

    No Known Activations