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

    Neuronpedia

    INDEX
    Explanations

    your relationship

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    啓
    0.46
    篦
    0.44
    視
    0.41
    QR
    0.41
    經典
    0.40
    ファー
    0.40
    ائها
    0.40
     mediate
    0.39
     inguinal
    0.39
     mediating
    0.39
    POSITIVE LOGITS
     besonderen
    0.45
    rift
    0.42
    ầng
    0.42
     Monaten
    0.42
    ṇ
    0.42
    edish
    0.42
    egrave
    0.42
    ōn
    0.41
    ọ
    0.40
     ļ
    0.40
    Act Density 0.000%

    No Known Activations