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

    Neuronpedia

    INDEX
    Explanations

    Markup

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     relying
    -0.09
     neglected
    -0.08
     fundamentally
    -0.08
     FMI
    -0.08
    istika
    -0.08
     verlassen
    -0.07
     nomination
    -0.07
    涵
    -0.07
     disciplin
    -0.07
     بمع
    -0.07
    POSITIVE LOGITS
     constructed
    0.08
    לו
    0.08
    Designed
    0.08
     তৈ
    0.08
    Portrait
    0.08
     несов
    0.08
    Created
    0.08
    ,json
    0.07
     Hele
    0.07
     cactus
    0.07
    Act Density 0.001%

    No Known Activations