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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ol
    -0.07
    �
    -0.07
     Nietzsche
    -0.06
     potatoes
    -0.06
     AVC
    -0.06
     текст
    -0.06
     Paste
    -0.06
     tun
    -0.06
     tunnel
    -0.06
    ATT
    -0.06
    POSITIVE LOGITS
    利用
    0.07
     Bearings
    0.06
     NS
    0.06
    (nd
    0.06
     ㅇ
    0.06
     getOrder
    0.06
     Sequence
    0.06
     stabilize
    0.06
    /qu
    0.06
    <TKey
    0.06
    Act Density 0.169%

    No Known Activations