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

    Neuronpedia

    INDEX
    Explanations

    contractions and possessives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     :,
    0.93
     /,
    0.88
     *)
    0.88
     *"
    0.84
     /(\
    0.83
     _)
    0.83
     /(
    0.82
     ܀
    0.82
     [*
    0.82
     [`
    0.78
    POSITIVE LOGITS
    ฯ
    0.85
    ‌ی
    0.82
     à
    0.81
    ®
    0.80
    ‪
    0.75
     próprio
    0.73
     إلى
    0.72
     marcher
    0.70
     الأمير
    0.70
    ¿
    0.69
    Act Density 0.311%

    No Known Activations