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

    Neuronpedia

    INDEX
    Explanations

    analyze and process data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     offensive
    0.45
     acquired
    0.44
     Client
    0.43
    sty
    0.43
     accommodating
    0.43
     experiencing
    0.42
     mediating
    0.41
     references
    0.41
     effective
    0.38
    0.38
    POSITIVE LOGITS
    耄
    0.47
    qPCR
    0.47
     มัน
    0.46
     vaikka
    0.46
     marvellous
    0.46
     જાય
    0.45
     masterpieces
    0.45
     લાખ
    0.44
     чудо
    0.44
    鎶
    0.44
    Act Density 0.004%

    No Known Activations