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

    Neuronpedia

    INDEX
    Explanations

    perform

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    day
    -0.07
     buyer
    -0.07
    tax
    -0.06
     Lucky
    -0.06
     cup
    -0.06
    radius
    -0.06
    >X
    -0.06
     Tax
    -0.06
     buckets
    -0.06
    直
    -0.06
    POSITIVE LOGITS
     performing
    0.21
     Perform
    0.20
    Perform
    0.18
     performed
    0.17
     perform
    0.16
    perform
    0.16
     performs
    0.15
     Performing
    0.15
     performers
    0.14
     performer
    0.13
    Act Density 0.052%

    No Known Activations