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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ب
    1.21
     TREAT
    0.80
    ق
    0.79
    מ
    0.75
     inhum
    0.75
     diad
    0.75
     condemns
    0.75
    ם
    0.74
     invigor
    0.73
     encroach
    0.73
    POSITIVE LOGITS
    亠
    0.97
     स्वरों
    0.90
    opcode
    0.88
    𝗈
    0.88
    programmer
    0.86
    otopy
    0.85
    ន៍
    0.85
     RCLCPP
    0.84
    xception
    0.84
    ोतरी
    0.84
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.