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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    _LEAVE
    -0.07
    Being
    -0.07
    只能说
    -0.07
    .kotlin
    -0.06
    ﮇ
    -0.06
    安抚
    -0.06
    عش
    -0.06
    🖍
    -0.06
    _PB
    -0.06
    cef
    -0.06
    POSITIVE LOGITS
    icker
    0.08
     Wor
    0.07
    achi
    0.07
     رسالة
    0.07
    纸
    0.07
    ateria
    0.07
    nier
    0.07
     tempor
    0.07
    ました
    0.06
    마
    0.06
    Act Density 0.008%

    No Known Activations