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

    Neuronpedia

    INDEX
    Explanations

    Dec

    np_max-act · gemini-2.0-flash

    This neuron detects the “Decided:” line (the “Dec” token marking the decision‐date header).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     TER
    -0.07
     TP
    -0.07
    _UT
    -0.07
     Nd
    -0.07
    _deps
    -0.06
    Leader
    -0.06
     П
    -0.06
    리아
    -0.06
    =A
    -0.06
    تين
    -0.06
    POSITIVE LOGITS
     İz
    0.07
     pop
    0.07
     BMC
    0.06
    嫌
    0.06
    อำนวย
    0.06
     licensors
    0.06
     exc
    0.06
    (sb
    0.06
     piger
    0.06
    ้ช
    0.06
    Act Density 0.001%

    No Known Activations