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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     enter
    0.73
     compel
    0.73
     curios
    0.72
     mash
    0.72
     odorless
    0.71
    образ
    0.70
     verso
    0.70
    ramble
    0.70
     Parses
    0.70
    л
    0.68
    POSITIVE LOGITS
    ⦿
    0.77
    arote
    0.74
     Granite
    0.73
    耀
    0.73
    AX
    0.71
    িক
    0.71
     concentrating
    0.71
     괜
    0.71
    擁
    0.70
    aisu
    0.70
    Act Density 0.000%

    No Known Activations