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
     orient
    -0.06
    ениями
    -0.06
     substitutions
    -0.06
     ach
    -0.06
     mb
    -0.06
     Sid
    -0.06
    .B
    -0.06
     AXIS
    -0.06
     taxing
    -0.06
    POSITIVE LOGITS
     ویژه
    0.08
    нолог
    0.07
    主要
    0.07
     PPP
    0.07
    /resources
    0.06
     pistol
    0.06
     Vulkan
    0.06
     attentive
    0.06
     děl
    0.06
    تغ
    0.06
    Act Density 0.000%

    No Known Activations