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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Alma
    -0.07
    支
    -0.07
    饪
    -0.07
    .Cross
    -0.07
    ummer
    -0.07
    ieties
    -0.07
    🙋
    -0.06
    ↵   ↵
    -0.06
     Wien
    -0.06
     לקרוא
    -0.06
    POSITIVE LOGITS
     intervals
    0.07
     оригина
    0.07
    久しぶり
    0.07
     +
↵
    0.06
    近期
    0.06
     Yug
    0.06
    拉开
    0.06
     stør
    0.06
    Past
    0.06
     yak
    0.06
    Act Density 0.043%

    No Known Activations