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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    つの
    -0.08
    _batch
    -0.07
     trails
    -0.07
     chapter
    -0.07
     surrounds
    -0.07
     truncated
    -0.07
    inars
    -0.07
    ivers
    -0.07
    _cases
    -0.07
    uint
    -0.07
    POSITIVE LOGITS
     pew
    0.07
     Degree
    0.07
     kto
    0.07
    colo
    0.07
    бел
    0.07
    قضا
    0.07
     qed
    0.07
    ߞ
    0.06
    ད
    0.06
    _Up
    0.06
    Act Density 0.004%

    No Known Activations