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

    Neuronpedia

    INDEX
    Explanations

    code block terminators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵
    1.18
    
    0.84
     Этот
    0.83
     Important
    0.79
     Wię
    0.79
     धोका
    0.78
     Οι
    0.75
     المهم
    0.75
     इम्यूनिटी
    0.74
    Important
    0.74
    POSITIVE LOGITS
     durchaus
    0.75
     enthusi
    0.71
    ලා
    0.67
     kont
    0.67
    ಷ್ಠ
    0.67
     bek
    0.66
     kommer
    0.65
    〉
    0.64
     crater
    0.64
    invest
    0.63
    Act Density 0.279%

    No Known Activations