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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    .extern
    -0.07
    办公厅
    -0.07
    かけて
    -0.07
    .Take
    -0.07
    TING
    -0.07
    bast
    -0.06
    钯
    -0.06
    ハ
    -0.06
     длин
    -0.06
    -Speed
    -0.06
    POSITIVE LOGITS
     한다
    0.07
    (trigger
    0.07
    .bl
    0.07
     Psychiatry
    0.06
    美丽乡村
    0.06
    .“
    0.06
     survivors
    0.06
     punishments
    0.06
    .vars
    0.06
    情节
    0.06
    Act Density 0.164%

    No Known Activations