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

    Neuronpedia

    INDEX
    Explanations

    Code Snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    踬
    -0.08
     MAK
    -0.07
    公用
    -0.07
    叫声
    -0.07
    ♨
    -0.06
     fileInfo
    -0.06
    饲
    -0.06
    窨
    -0.06
     ראשי
    -0.06
    ตำแ
    -0.06
    POSITIVE LOGITS
    >().
    0.08
    talk
    0.07
    :///
    0.07
    	model
    0.07
    Tutorial
    0.07
    eprom
    0.06
     '''
↵
    0.06
    自主研发
    0.06
    只不过是
    0.06
    .scalatest
    0.06
    Act Density 0.003%

    No Known Activations