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

    Neuronpedia

    INDEX
    Explanations

    sequences and beginnings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ግሎ
    1.18
     FabD
    1.18
     miedo
    1.17
     लागू
    1.15
     SKSpriteNode
    1.13
    旨在
    1.12
     پوکر
    1.12
    quee
    1.11
     друга
    1.10
    𝖒
    1.09
    POSITIVE LOGITS
    Have
    1.09
    写真は
    1.09
     certainly
    1.04
     have
    1.00
     Have
    0.99
     berat
    0.99
    மணி
    0.98
     minimal
    0.95
     Какой
    0.94
    AR
    0.93
    Act Density 0.001%

    No Known Activations