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

    Neuronpedia

    INDEX
    Explanations

    journal publication dates

    np_max-act · gemini-2.0-flash

    The neuron responds to four-digit numeric tokens that denote publication years in citations.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Printing
    -0.07
    oil
    -0.06
    .Big
    -0.06
     �
    -0.06
    Fizz
    -0.06
     Pill
    -0.06
    ＊
    -0.06
     pathology
    -0.06
     pulmonary
    -0.06
     Clarkson
    -0.06
    POSITIVE LOGITS
    ITIONS
    0.08
    _ROOM
    0.07
    arin
    0.06
    apot
    0.06
    Qualified
    0.06
     mysqli
    0.06
    hle
    0.06
    ');
    0.06
     flavor
    0.06
    UR
    0.06
    Act Density 0.006%

    No Known Activations