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

    Neuronpedia

    INDEX
    Explanations

    configuration or parameters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     GoObject
    0.50
     개발
    0.43
    ≈
    0.41
     бумаги
    0.40
    dropBtn
    0.40
     spineItem
    0.39
    ιών
    0.38
    ব্যব
    0.38
     約
    0.37
    的一切
    0.37
    POSITIVE LOGITS
    யின்
    0.49
     asta
    0.46
     desses
    0.45
     indien
    0.45
     anderen
    0.44
     anden
    0.44
     andra
    0.44
     vais
    0.44
     instaur
    0.44
     ilk
    0.44
    Act Density 0.005%

    No Known Activations