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

    Neuronpedia

    INDEX
    Explanations

    mathematical and scientific units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     palate
    0.50
     bero
    0.49
     encephal
    0.46
     redox
    0.46
    ั
    0.46
     tokamak
    0.45
     گاز
    0.45
     kerusakan
    0.44
     brute
    0.44
     aberration
    0.43
    POSITIVE LOGITS
    tak
    0.55
    신
    0.51
    dent
    0.46
    둣
    0.46
    사람
    0.46
    요
    0.45
    리를
    0.45
    transform
    0.45
    seller
    0.44
    تقديم
    0.44
    Act Density 0.031%

    No Known Activations