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

    Neuronpedia

    INDEX
    Explanations

    visuals or images

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     monoxide
    0.38
     Calcd
    0.35
    िप
    0.35
     Ấn
    0.35
    Initializing
    0.34
    rencies
    0.34
     Coding
    0.34
     RuntimeError
    0.34
    ിലോ
    0.33
     reactive
    0.33
    POSITIVE LOGITS
     photographs
    2.80
     photos
    2.70
     사진
    2.66
     фотографии
    2.66
     pictures
    2.64
     fotos
    2.58
     photograph
    2.52
    图片
    2.50
    照片
    2.47
     foto
    2.42
    Act Density 0.014%

    No Known Activations