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

    Neuronpedia

    INDEX
    Explanations

    programming

    np_max-act · gemini-2.0-flash

    This neuron activates on special sequence tokens and markup delimiters (e.g., `<|...|>` markers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .query
    -0.07
    .ps
    -0.06
    _sms
    -0.06
    ció
    -0.06
    _cm
    -0.06
    ảm
    -0.06
     ==>
    -0.06
    .files
    -0.06
    Resize
    -0.06
     flotation
    -0.06
    POSITIVE LOGITS
    (Buffer
    0.07
    �
    0.06
     CHO
    0.06
     Poster
    0.06
     Credit
    0.06
    只
    0.06
     Contin
    0.06
    Print
    0.06
     انتخاب
    0.06
     Aster
    0.06
    Act Density 0.049%

    No Known Activations