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

    Neuronpedia

    INDEX
    Explanations

    high, then qualifier

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AREA
    0.45
     permeability
    0.44
     Qualität
    0.44
     정도
    0.42
     kaliteli
    0.42
     GRADE
    0.42
     Mouth
    0.42
     quality
    0.42
     loads
    0.42
    Quality
    0.42
    POSITIVE LOGITS
     brow
    0.66
    brow
    0.64
     stakes
    0.64
    stakes
    0.57
    Brow
    0.57
    oct
    0.54
    flying
    0.54
     Browne
    0.53
     Stakes
    0.52
     flying
    0.51
    Act Density 0.016%

    No Known Activations