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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    струк
    -0.07
     इत
    -0.06
    InRange
    -0.06
     ra
    -0.06
    Teams
    -0.06
     soils
    -0.06
     avi
    -0.06
     grandchildren
    -0.06
     aliens
    -0.06
    odelist
    -0.05
    POSITIVE LOGITS
    Merchant
    0.07
    /callback
    0.07
     Theresa
    0.07
     swings
    0.07
     hele
    0.06
     MONTH
    0.06
    .Fetch
    0.06
    宅
    0.06
    整个
    0.06
     symptom
    0.06
    Act Density 0.103%

    No Known Activations