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

    Neuronpedia

    INDEX
    Explanations

    why you might

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Compensation
    0.49
     consigned
    0.45
    ﻮ
    0.45
    Deliver
    0.45
    WithString
    0.44
    title
    0.44
     sidelined
    0.44
     بالنسبه
    0.44
    scrire
    0.44
     szükség
    0.43
    POSITIVE LOGITS
     ti
    0.48
     Ti
    0.46
     DDS
    0.44
     並
    0.42
     hypothalamus
    0.41
    ◝
    0.41
    邏
    0.41
     carinatis
    0.40
    ↣
    0.40
    امہ
    0.40
    Act Density 0.003%

    No Known Activations