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

    Neuronpedia

    INDEX
    Explanations

    following year 1

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Ache
    0.76
    <img>
    0.74
     বটে
    0.73
    İY
    0.70
     Remembering
    0.70
    朢
    0.66
    நக
    0.66
    囦
    0.65
     worrisome
    0.65
     forgetting
    0.65
    POSITIVE LOGITS
     १०
    0.89
    🔟
    0.83
     fellowship
    0.80
    컨
    0.78
    ли
    0.77
     المج
    0.77
    शिवम
    0.77
    ливо
    0.76
    दस
    0.75
    лива
    0.74
    Act Density 0.004%

    No Known Activations