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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    锄
    -0.07
    _integral
    -0.07
    abis
    -0.07
     zn
    -0.07
     BST
    -0.06
     cleaning
    -0.06
    стран
    -0.06
     defence
    -0.06
     faster
    -0.06
     GPA
    -0.06
    POSITIVE LOGITS
    ({
↵
    0.08
    目睹
    0.07
     üzerine
    0.07
    ({↵
    0.07
    willReturn
    0.07
    shouldReceive
    0.07
    |"
    0.07
    (("
    0.07
    issue
    0.07
    👪
    0.07
    Act Density 0.058%

    No Known Activations