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

    Neuronpedia

    INDEX
    Explanations

    betting

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is detect mentions of placing or specifying a wager (e.g. “wager,” “bet,” “amount,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _fid
    -0.08
    Rand
    -0.07
    Longitude
    -0.06
     Cait
    -0.06
     DPS
    -0.06
    (copy
    -0.06
    qed
    -0.06
     TripAdvisor
    -0.06
     DPR
    -0.06
     研
    -0.06
    POSITIVE LOGITS
     والت
    0.07
     wishing
    0.06
     {?}
    0.06
    개를
    0.06
    اوند
    0.06
     goes
    0.06
     concerns
    0.06
    _sum
    0.06
    させ
    0.06
    unun
    0.06
    Act Density 0.010%

    No Known Activations