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

    Neuronpedia

    INDEX
    Explanations

    ()

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     babe
    -0.07
    駅徒歩
    -0.07
     aft
    -0.07
     identifier
    -0.06
     leopard
    -0.06
    larım
    -0.06
    杯
    -0.06
     سور
    -0.06
     푸
    -0.06
    "As
    -0.06
    POSITIVE LOGITS
    .emit
    0.07
    .Card
    0.06
    <Scalar
    0.06
     Fine
    0.06
    ure
    0.06
    (contract
    0.06
    (logging
    0.06
     pět
    0.06
     giảng
    0.06
    <dynamic
    0.06
    Act Density 0.013%

    No Known Activations