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

    Neuronpedia

    INDEX
    Explanations

    deed, deeds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ه
    0.98
    یت
    0.86
    تی
    0.83
    یس
    0.82
    ０
    0.80
    سی
    0.80
    हरु
    0.79
    is
    0.78
    t
    0.77
    हरू
    0.75
    POSITIVE LOGITS
    s
    0.84
     =
    0.77
    ed
    0.77
     过
    0.75
     \&
    0.75
    ný
    0.74
     powied
    0.74
     البي
    0.73
     }
    0.73
     of
    0.72
    Act Density 0.002%

    No Known Activations