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

    Neuronpedia

    INDEX
    Explanations

    can do or translate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :
    0.68
     E
    0.59
     Wisdom
    0.58
     D
    0.57
    +
    0.57
     Ch
    0.55
     &
    0.55
     Life
    0.55
     Rose
    0.54
     Rush
    0.53
    POSITIVE LOGITS
     ejecutar
    0.58
    ﻭ
    0.55
     marít
    0.52
    ନ୍
    0.50
    抒
    0.50
     rame
    0.50
     oliva
    0.50
    ুদ
    0.49
     semelh
    0.49
     )।
    0.49
    Act Density 0.255%

    No Known Activations