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

    Neuronpedia

    INDEX
    Explanations

    code structures and phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    觜
    0.44
    Blake
    0.41
    呷
    0.41
    рию
    0.41
    Ⴊ
    0.41
    Chlor
    0.40
    パート
    0.40
    Concept
    0.39
    Companion
    0.39
     ಕರೆ
    0.39
    POSITIVE LOGITS
     Gü
    0.42
     Valencia
    0.40
     Evening
    0.38
     sequ
    0.38
     online
    0.38
     năm
    0.38
     Guangzhou
    0.38
     ejected
    0.37
     Australia
    0.37
     influenza
    0.37
    Act Density 0.008%

    No Known Activations