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

    Neuronpedia

    INDEX
    Explanations

    article

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .format
    -0.07
    ่ำ
    -0.07
    PostBack
    -0.07
    	Runtime
    -0.07
     помощи
    -0.06
    _Format
    -0.06
     đ
    -0.06
     الشم
    -0.06
    _td
    -0.06
     ナ
    -0.06
    POSITIVE LOGITS
     repealed
    0.06
    stop
    0.06
    Decoration
    0.06
     Streams
    0.06
    Stop
    0.06
     Reform
    0.06
    �
    0.06
     fifty
    0.06
    oral
    0.06
    )])↵
    0.06
    Act Density 0.025%

    No Known Activations