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

    Neuronpedia

    INDEX
    Explanations

    recently discovered

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kệ
    0.83
     prove
    0.77
     proves
    0.74
    Prove
    0.74
     Jahrhunderts
    0.72
     प्रूव
    0.72
     Prove
    0.71
    뀔
    0.71
     outperforms
    0.71
    AnalyzeAction
    0.70
    POSITIVE LOGITS
     recently
    1.61
     stumbled
    1.59
     noticed
    1.37
     encountered
    1.32
     discovered
    1.29
    recently
    1.28
     wanted
    1.28
    Recently
    1.24
     purchased
    1.23
    最近
    1.22
    Act Density 0.800%

    No Known Activations