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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    汲
    -0.07
     tion
    -0.07
    Math
    -0.07
    hidden
    -0.07
     Selected
    -0.07
    select
    -0.07
     stationary
    -0.07
    Support
    -0.07
     sustainable
    -0.07
     هناك
    -0.06
    POSITIVE LOGITS
     Iranians
    0.07
    雱
    0.07
     uçu
    0.07
    ≴
    0.06
    곬
    0.06
    לאומי
    0.06
     Zhao
    0.06
     menus
    0.06
     proved
    0.06
     scram
    0.06
    Act Density 0.001%

    No Known Activations