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

    Neuronpedia

    INDEX
    Explanations

    say "let" words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    规
    -0.07
    -step
    -0.07
     recommend
    -0.07
     Suppose
    -0.07
     supervised
    -0.07
     occurred
    -0.07
     suppose
    -0.07
     McKenzie
    -0.06
     plumbing
    -0.06
    =com
    -0.06
    POSITIVE LOGITS
     เ�
    0.06
    lessons
    0.06
    <<"\
    0.06
    EventManager
    0.06
    дя
    0.06
     �
    0.05
    xde
    0.05
    080
    0.05
     keypoints
    0.05
     ByteString
    0.05
    Act Density 0.008%

    No Known Activations