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

    Neuronpedia

    INDEX
    Explanations

    about explanations and continuations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dinner
    0.46
     infectious
    0.45
    해
    0.45
    는
    0.44
    দ
    0.44
     binding
    0.43
     leaning
    0.43
     critical
    0.42
     helped
    0.41
     parliament
    0.41
    POSITIVE LOGITS
     stockbild
    0.58
    Literatur
    0.55
    㳳
    0.52
    Comparison
    0.52
     jedoch
    0.51
    Imaging
    0.51
     modele
    0.51
    Colors
    0.51
     خاصة
    0.50
    Categoria
    0.50
    Act Density 0.001%

    No Known Activations