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

    Neuronpedia

    INDEX
    Explanations

    reels

    np_max-act · gemini-2.0-flash

    This neuron detects numerical tokens and quantitative values (e.g. numbers for reels, paylines, ways to win, payouts, etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     released
    -0.08
    ategorized
    -0.07
     Cir
    -0.06
     QUE
    -0.06
    leased
    -0.06
     quelle
    -0.06
     sprites
    -0.06
     regulators
    -0.06
     advocates
    -0.06
     vou
    -0.06
    POSITIVE LOGITS
    _FIELD
    0.07
    =start
    0.07
    .appcompat
    0.06
    πη
    0.06
     Screening
    0.06
    _ATTACK
    0.06
    $ar
    0.06
    ợ
    0.06
     ENTITY
    0.06
     Launch
    0.06
    Act Density 0.002%

    No Known Activations