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

    Neuronpedia

    INDEX
    Explanations

    historical figures and technological terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     மன்ன
    0.47
    맑
    0.46
     gangsters
    0.46
     desktops
    0.43
     نفسي
    0.43
    苌
    0.43
     diapers
    0.42
    Ǧ
    0.42
     HTMLSc
    0.42
     درخت
    0.42
    POSITIVE LOGITS
    define
    0.40
    ությ
    0.40
     clave
    0.40
    show
    0.39
    cher
    0.39
    i
    0.39
    ítica
    0.38
    selling
    0.38
    day
    0.38
    vis
    0.37
    Act Density 0.001%

    No Known Activations