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

    Neuronpedia

    INDEX
    Explanations

    Weighing to find counterfeit

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ’esp
    -0.08
    bul
    -0.08
     قابلیت
    -0.08
     асп
    -0.08
    Bul
    -0.08
     куп
    -0.08
    'esp
    -0.08
     bullets
    -0.07
     composed
    -0.07
     fitur
    -0.07
    POSITIVE LOGITS
    結果
    0.09
    _result
    0.09
     resulted
    0.08
    结果
    0.08
    	result
    0.08
    Detected
    0.08
     결과
    0.08
    	change
    0.08
    _detect
    0.08
    是哪
    0.08
    Act Density 0.003%

    No Known Activations