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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     arg
    -0.07
    .AddComponent
    -0.07
    _FS
    -0.07
    cri
    -0.07
     PIX
    -0.07
     ----------↵
    -0.06
    项
    -0.06
    staw
    -0.06
     الخيار
    -0.06
     reload
    -0.06
    POSITIVE LOGITS
    _GT
    0.07
    _minutes
    0.07
     incess
    0.06
    🇰
    0.06
     yayımla
    0.06
    ้อย
    0.06
    _derivative
    0.06
    AMESPACE
    0.06
    Ⲩ
    0.06
    infos
    0.06
    Act Density 0.019%

    No Known Activations