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

    Neuronpedia

    INDEX
    Explanations

    colon

    np_max-act · gemini-2.0-flash

    The neuron detects interlanguage‐link tokens (language‐code markers and their colons) in wiki‐style pages.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Sch
    -0.08
    _platform
    -0.07
    Caps
    -0.07
    .Pe
    -0.06
    _selection
    -0.06
    Expires
    -0.06
     Sch
    -0.06
    folder
    -0.06
    _SF
    -0.06
     도
    -0.06
    POSITIVE LOGITS
    атар
    0.06
     imu
    0.06
    "){↵
    0.06
     Dry
    0.06
    aea
    0.06
    таж
    0.06
     impass
    0.06
    .MapFrom
    0.06
    baş
    0.06
    aggi
    0.06
    Act Density 0.002%

    No Known Activations