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

    Neuronpedia

    INDEX
    Explanations

    To help me

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    美丽的
    0.86
     جميلة
    0.74
     touted
    0.74
     đẹp
    0.74
     boasted
    0.73
     undetected
    0.72
     proclaims
    0.72
     publicités
    0.71
     wahr
    0.71
     pozor
    0.70
    POSITIVE LOGITS
     help
    1.62
    help
    1.45
    帮助
    1.44
    Help
    1.41
     Help
    1.40
     helps
    1.33
     HELP
    1.29
    幫助
    1.27
     ajuda
    1.22
     membantu
    1.21
    Act Density 0.414%

    No Known Activations