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

    Neuronpedia

    INDEX
    Explanations

    silky smooth manner

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fizer
    0.77
     seats
    0.76
     hypersurfaces
    0.75
    Ссы
    0.75
    िश्वत
    0.75
     Assistants
    0.75
     Leur
    0.74
     tegas
    0.73
    বেন
    0.72
     Einwill
    0.71
    POSITIVE LOGITS
    ש
    1.06
    y
    0.99
    av
    0.94
    ە
    0.92
    é
    0.90
    t
    0.88
    ح
    0.87
    alı
    0.86
    ্লাস
    0.86
    ythe
    0.86
    Act Density 0.000%

    No Known Activations