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

    Neuronpedia

    INDEX
    Explanations

    Formal documents with symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ?type
    -0.07
    urile
    -0.07
    ("---
    -0.07
     engel
    -0.06
     پیامبر
    -0.06
     Johan
    -0.06
    ).__
    -0.06
    ellites
    -0.06
    giatan
    -0.06
    icrous
    -0.06
    POSITIVE LOGITS
    Func
    0.07
    较
    0.07
    component
    0.07
    (let
    0.06
    Samples
    0.06
     MPS
    0.06
     Newly
    0.06
    家
    0.06
    fos
    0.06
    _ob
    0.06
    Act Density 0.000%

    No Known Activations