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

    Neuronpedia

    INDEX
    Explanations

    AI descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    似乎
    0.46
    淉
    0.40
    imental
    0.40
     গল
    0.39
     LinearLayout
    0.39
    显示的
    0.39
    琏
    0.38
    bandSize
    0.38
     Logical
    0.38
    䀼
    0.37
    POSITIVE LOGITS
     celebrities
    0.52
     IMAX
    0.50
     uso
    0.48
     cidad
    0.48
    namento
    0.48
     journée
    0.48
     ടി
    0.47
     imprescind
    0.47
     deceiving
    0.47
     considéré
    0.46
    Act Density 0.001%

    No Known Activations