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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric tokens (e.g. years, volumes, page numbers, and other numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    15
    -0.07
     STRICT
    -0.07
    Refresh
    -0.07
    16
    -0.07
    INF
    -0.07
     Thanh
    -0.06
    TCHA
    -0.06
     LIN
    -0.06
    entifier
    -0.06
     lbl
    -0.06
    POSITIVE LOGITS
    ایع
    0.06
    Originally
    0.06
    anders
    0.06
     pesso
    0.06
    ibrary
    0.06
     tesis
    0.06
    比例
    0.06
    ｌ
    0.06
     Δημο
    0.06
    opped
    0.06
    Act Density 0.017%

    No Known Activations