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

    Neuronpedia

    INDEX
    Explanations

    war

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    oru
    -0.07
    cloud
    -0.06
     ö
    -0.06
     κορ
    -0.06
     surrendered
    -0.06
     Seats
    -0.06
     tension
    -0.06
     accomp
    -0.06
     ενός
    -0.06
     Famil
    -0.06
    POSITIVE LOGITS
     Loài
    0.07
     Ripple
    0.06
     letting
    0.06
    (unique
    0.06
    尚
    0.06
    ์น
    0.06
    ودة
    0.06
    균
    0.06
     ItemType
    0.06
    ----↵
    0.06
    Act Density 0.028%

    No Known Activations