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

    Neuronpedia

    INDEX
    Explanations

    Okay, initiating explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     päät
    0.68
    빵
    0.68
     Toronto
    0.63
     intersection
    0.63
     센터
    0.63
    مركز
    0.62
    Stations
    0.62
     intersect
    0.60
     Journals
    0.60
     sht
    0.60
    POSITIVE LOGITS
    Submit
    0.76
    解答
    0.74
     Submit
    0.73
     Let
    0.67
    ochem
    0.66
    submit
    0.66
     వివ
    0.66
     Ask
    0.65
     Vedi
    0.65
     কৃষি
    0.64
    Act Density 0.199%

    No Known Activations