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

    Neuronpedia

    INDEX
    Explanations

    series, expansion, progression

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    im
    1.16
    n
    1.01
    k
    0.99
    l
    0.98
    em
    0.93
    ub
    0.93
    ah
    0.91
    is
    0.90
    daki
    0.90
    ن
    0.90
    POSITIVE LOGITS
    ляє
    0.83
    Misc
    0.80
    Elig
    0.79
     жүктөө
    0.79
     DGP
    0.77
    ्स
    0.76
    AndUpdate
    0.76
     кило
    0.76
    arska
    0.76
    慈善
    0.75
    Act Density 0.001%

    No Known Activations