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

    Neuronpedia

    INDEX
    Explanations

    401

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of contributing to retirement accounts (e.g. “401(k)”, “IRA”)—i.e. tokens relating to retirement-plan contributions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ้าของ
    -0.07
    arc
    -0.06
     buffers
    -0.06
     MQ
    -0.06
    _ptrs
    -0.06
    肩
    -0.06
     préc
    -0.06
     lexer
    -0.06
    雙
    -0.06
     weekend
    -0.06
    POSITIVE LOGITS
    401
    0.08
     DNS
    0.07
    $('
    0.07
    DNS
    0.06
    Veter
    0.06
     рыб
    0.06
     ovliv
    0.06
    nos
    0.06
     insightful
    0.06
     Covent
    0.06
    Act Density 0.001%

    No Known Activations