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

    Neuronpedia

    INDEX
    Explanations

    efficiency

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <File
    -0.07
    <span
    -0.06
    span
    -0.06
     chatt
    -0.06
    Card
    -0.06
     �
    -0.06
     recur
    -0.06
     Talk
    -0.06
    _RUNTIME
    -0.05
    List
    -0.05
    POSITIVE LOGITS
     efficiency
    0.16
     Efficiency
    0.13
     efficiencies
    0.13
     Released
    0.08
    (shift
    0.07
     kiện
    0.07
    ifecycle
    0.07
    효
    0.07
    ensi
    0.07
    -efficient
    0.07
    Act Density 0.007%

    No Known Activations