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

    Neuronpedia

    INDEX
    Explanations

    historical events

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     contracts
    -0.06
     mantle
    -0.06
    кус
    -0.06
     Chem
    -0.06
    ially
    -0.06
     朝
    -0.06
     whenever
    -0.06
     shines
    -0.06
     kinds
    -0.06
     joking
    -0.06
    POSITIVE LOGITS
    (",
    0.07
    ashington
    0.07
     آهنگ
    0.06
    (',
    0.06
    осред
    0.06
     під
    0.06
    .Mapping
    0.06
    UpEdit
    0.06
     trụ
    0.06
    بر
    0.06
    Act Density 0.046%

    No Known Activations