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

    Neuronpedia

    INDEX
    Explanations

    484

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (ai
    -0.08
     localhost
    -0.07
    /"+
    -0.07
     Nu
    -0.07
     frequently
    -0.06
    ↵
    -0.06
     WIN
    -0.06
     =================================================
    -0.06
    ServiceProvider
    -0.06
     oy
    -0.06
    POSITIVE LOGITS
     Также
    0.07
    jištění
    0.06
     Michele
    0.06
    ίος
    0.06
    іл
    0.06
     tart
    0.06
    머니
    0.06
    basket
    0.06
    "encoding
    0.06
    anno
    0.06
    Act Density 0.010%

    No Known Activations