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

    Neuronpedia

    INDEX
    Explanations

    quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     contentious
    -0.08
    ทดสอบ
    -0.07
     ante
    -0.07
    浪潮
    -0.07
    _LVL
    -0.07
    👁
    -0.07
     Fitz
    -0.07
    בינו
    -0.07
    eut
    -0.07
     reluct
    -0.06
    POSITIVE LOGITS
    	System
    0.07
    ха
    0.07
    ],
↵
    0.06
    -grow
    0.06
    ברים
    0.06
    헷
    0.06
    オ
    0.06
     ',↵
    0.06
     resulted
    0.06
    лект
    0.06
    Act Density 0.001%

    No Known Activations