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

    Neuronpedia

    INDEX
    Explanations

    images and customization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     arginine
    0.43
     murderous
    0.43
     trastornos
    0.42
     virulent
    0.41
     alkaloids
    0.41
     neurotic
    0.39
     matem
    0.39
     enzimas
    0.38
     inhomogeneities
    0.38
     nitrog
    0.38
    POSITIVE LOGITS
     customizable
    0.54
    浏览
    0.52
    自定义
    0.49
     clickable
    0.49
     browse
    0.49
     automatically
    0.48
     Click
    0.47
     preview
    0.46
     Dashboard
    0.46
     display
    0.46
    Act Density 0.642%

    No Known Activations