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

    Neuronpedia

    INDEX
    Explanations

    ran

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     showers
    -0.07
    "),"
    -0.07
    Jack
    -0.07
    .CommandText
    -0.06
     stresses
    -0.06
    경제
    -0.06
    ↵
    -0.06
     Specific
    -0.06
     ارتف
    -0.06
     TOUR
    -0.06
    POSITIVE LOGITS
     dern
    0.07
     bols
    0.07
     setLoading
    0.07
    гра
    0.06
     Kim
    0.06
     mates
    0.06
    POCH
    0.06
     plight
    0.06
     scrim
    0.06
    (){}↵↵
    0.06
    Act Density 0.006%

    No Known Activations