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

    Neuronpedia

    INDEX
    Explanations

    SELECT COUNT

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ق
    0.54
    හෙ
    0.50
    ड्या
    0.50
    垻
    0.49
    ણી
    0.48
     esfuerzos
    0.47
    ସ
    0.47
    פן
    0.45
    ﻻ
    0.45
    ДИ
    0.45
    POSITIVE LOGITS
    newEvent
    0.47
    newL
    0.44
     S
    0.42
     torn
    0.42
     न्यू
    0.41
     New
    0.40
    k
    0.40
     Hoi
    0.39
    etr
    0.39
     Essay
    0.39
    Act Density 0.001%

    No Known Activations