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

    Neuronpedia

    INDEX
    Explanations

    travel activities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     والتي
    -0.07
    	Z
    -0.07
    dump
    -0.07
     والذي
    -0.07
    ModelProperty
    -0.06
     quienes
    -0.06
    .twig
    -0.06
    multipart
    -0.06
     dong
    -0.06
    .timing
    -0.06
    POSITIVE LOGITS
    esor
    0.08
     orb
    0.07
    سة
    0.07
     Gover
    0.07
    orer
    0.07
    榜样
    0.07
    _INET
    0.07
    chantment
    0.06
    สว
    0.06
    (Book
    0.06
    Act Density 0.057%

    No Known Activations