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

    Neuronpedia

    INDEX
    Explanations

    quick learning and abilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     exclusively
    0.43
    exclusive
    0.42
     exclusive
    0.41
     billboards
    0.40
     subclasses
    0.39
     births
    0.38
     downloaded
    0.38
     downloads
    0.38
     frequencies
    0.38
     bitmaps
    0.37
    POSITIVE LOGITS
     ability
    1.13
     willingness
    1.02
     adaptability
    1.01
     Ability
    0.97
     способность
    0.96
     способности
    0.95
     eagerness
    0.95
    Ability
    0.91
     tenacity
    0.82
     acumen
    0.81
    Act Density 0.034%

    No Known Activations