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

    Neuronpedia

    INDEX
    Explanations

    surge

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ål
    -0.08
    lass
    -0.07
    stial
    -0.07
    래스
    -0.07
    玩
    -0.07
    KN
    -0.07
    -collection
    -0.07
    DAO
    -0.06
     invalidate
    -0.06
    lean
    -0.06
    POSITIVE LOGITS
     serge
    0.08
    okoj
    0.07
     sphere
    0.07
     Serge
    0.07
     succesfully
    0.07
    しており
    0.07
     Curve
    0.07
    ové
    0.06
     verdienen
    0.06
    ';
↵
    0.06
    Act Density 0.004%

    No Known Activations