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

    Neuronpedia

    INDEX
    Explanations

    succession/inheriting titles

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric tokens—years, dates, ordinal indicators, and other numbers—in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     UW
    -0.07
     Berlin
    -0.07
     Wrest
    -0.06
     warranties
    -0.06
     गई
    -0.06
     vět
    -0.06
     Sonic
    -0.06
     �
    -0.06
     Pakistan
    -0.06
    _STATUS
    -0.06
    POSITIVE LOGITS
    ayız
    0.07
    }%
    0.07
    neğin
    0.06
    istrar
    0.06
    Background
    0.06
    /problem
    0.06
    ofstream
    0.06
     PCB
    0.06
    UserCode
    0.06
     PLC
    0.06
    Act Density 0.024%

    No Known Activations