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

    Neuronpedia

    INDEX
    Explanations

    historical contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mastered
    0.42
     noticeably
    0.41
     خبری
    0.41
     regenerating
    0.39
     striking
    0.39
    ↵
    0.37
    师傅
    0.37
     gained
    0.37
    कडे
    0.37
     deploying
    0.37
    POSITIVE LOGITS
    History
    0.79
    history
    0.79
    histor
    0.75
     истори
    0.74
     ইতিহাস
    0.74
     істори
    0.74
    geschichte
    0.73
     histori
    0.73
     История
    0.73
     History
    0.73
    Act Density 0.018%

    No Known Activations