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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    뻥
    -0.07
    reasonable
    -0.07
    쎼
    -0.07
     apro
    -0.07
    🍝
    -0.07
     Vale
    -0.07
    .RestController
    -0.07
    曉
    -0.07
    ystack
    -0.07
    ڭ
    -0.06
    POSITIVE LOGITS
     brutality
    0.08
     neutrality
    0.08
    elu
    0.07
     mentality
    0.07
    ته
    0.07
    %%↵
    0.07
    人たち
    0.07
    糅
    0.07
     ellos
    0.07
    hx
    0.07
    Act Density 0.044%

    No Known Activations