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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    🦊
    -0.07
     SEG
    -0.07
     التعا
    -0.07
    有點
    -0.07
    _pi
    -0.07
    IMG
    -0.07
    ﺥ
    -0.07
    筦
    -0.07
     مو
    -0.07
    слож
    -0.07
    POSITIVE LOGITS
    iagnostics
    0.08
    弟弟
    0.07
     criminal
    0.07
    ("")↵
    0.07
    惮
    0.07
    实
    0.07
    سطين
    0.07
    tréal
    0.07
     ben
    0.07
    erne
    0.07
    Act Density 0.108%

    No Known Activations