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

    Neuronpedia

    INDEX
    Explanations

    legal cases

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    اين
    -0.07
    plementation
    -0.07
    .com
    -0.07
    -core
    -0.07
    Norm
    -0.07
    	curr
    -0.06
    ош
    -0.06
     metro
    -0.06
    sense
    -0.06
    	core
    -0.06
    POSITIVE LOGITS
    .redis
    0.07
    �
    0.07
    �
    0.06
     Hawaiian
    0.06
     第三
    0.06
     ModelState
    0.06
    FieldName
    0.06
    在线视频
    0.06
     文章
    0.06
     doPost
    0.06
    Act Density 0.006%

    No Known Activations