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

    Neuronpedia

    INDEX
    Explanations

    protection

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .advance
    -0.07
    ove
    -0.07
     Coalition
    -0.07
    ⋱
    -0.07
    �
    -0.06
    uber
    -0.06
    _download
    -0.06
    comic
    -0.06
    言
    -0.06
    ie
    -0.06
    POSITIVE LOGITS
    伙伴关系
    0.07
    产品质量
    0.07
    -en
    0.07
    
↵
    0.07
    >

↵
    0.07
     gastr
    0.07
    	except
    0.07
     enhances
    0.07
     less
    0.07
    عد
    0.07
    Act Density 0.012%

    No Known Activations