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
     Holiday
    -0.07
     Coverage
    -0.07
    ‌شن
    -0.07
     signatures
    -0.06
     coverage
    -0.06
     aficion
    -0.06
    Accuracy
    -0.06
    xcc
    -0.06
     Armour
    -0.06
     sap
    -0.06
    POSITIVE LOGITS
     nails
    0.08
     intestine
    0.07
    [OF
    0.06
     tiến
    0.06
    惊
    0.06
     fileId
    0.06
    rov
    0.06
     شود
    0.06
     DUI
    0.06
     كرة
    0.06
    Act Density 0.027%

    No Known Activations