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

    Neuronpedia

    INDEX
    Explanations

    formulas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	request
    -0.07
    glm
    -0.06
     Compute
    -0.06
    Debe
    -0.06
     lu
    -0.06
    prime
    -0.06
     blades
    -0.06
     destroy
    -0.06
     EntryPoint
    -0.06
    xDF
    -0.06
    POSITIVE LOGITS
     diferentes
    0.07
     itemprop
    0.07
    基于
    0.07
    (WebDriver
    0.07
    (unit
    0.07
    _lvl
    0.06
     پیشینه
    0.06
    )\<
    0.06
     monopol
    0.06
    Polit
    0.06
    Act Density 0.093%

    No Known Activations