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

    Neuronpedia

    INDEX
    Explanations

    research papers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     XF
    -0.07
    资源
    -0.07
     MyClass
    -0.06
    _summary
    -0.06
     akan
    -0.06
     sera
    -0.06
    _categories
    -0.06
     deutschland
    -0.06
     terminals
    -0.06
     οποίο
    -0.06
    POSITIVE LOGITS
     Α
    0.07
     باب
    0.07
     oppression
    0.07
    �
    0.07
     �
    0.06
     culp
    0.06
     entonces
    0.06
     جام
    0.06
     vary
    0.06
     Appalachian
    0.06
    Act Density 0.003%

    No Known Activations