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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    تأسي
    -0.08
    听力
    -0.07
    SELF
    -0.07
    (namespace
    -0.07
    if
    -0.07
    (TAG
    -0.06
    'acc
    -0.06
     skys
    -0.06
     Tall
    -0.06
    ffc
    -0.06
    POSITIVE LOGITS
     =
    0.10
     Она
    0.08
     ,
    0.08
    =#
    0.08
    셢
    0.07
    很低
    0.07
    =d
    0.07
    ▽
    0.07
     اللازمة
    0.07
    以致
    0.07
    Act Density 0.205%

    No Known Activations