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

    Neuronpedia

    INDEX
    Explanations

    strategies and techniques

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nhàng
    0.39
    所谓
    0.38
     ঘন্টার
    0.37
     ঘণ্টার
    0.36
    Emo
    0.35
    PMorgan
    0.35
     الحياة
    0.35
    電荷
    0.35
     hadir
    0.34
    破解
    0.34
    POSITIVE LOGITS
    wl
    0.44
     escritores
    0.42
    iii
    0.39
     yaad
    0.38
     Confeder
    0.38
    潙
    0.38
    ii
    0.38
    nota
    0.38
     ബ്രി
    0.37
     republik
    0.37
    Act Density 0.001%

    No Known Activations