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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     млн
    -0.08
     ער
    -0.07
    שתמש
    -0.07
    菏
    -0.07
    奇特
    -0.07
    עשי
    -0.07
     дир
    -0.07
    _operand
    -0.07
     phẩm
    -0.06
    orst
    -0.06
    POSITIVE LOGITS
     unsur
    0.07
    (dtype
    0.07
     MacBook
    0.07
    oub
    0.07
    _received
    0.06
    -dev
    0.06
     bab
    0.06
     QR
    0.06
    缭
    0.06
    Effects
    0.06
    Act Density 0.005%

    No Known Activations