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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     SELECT
    -0.08
     för
    -0.08
    投诉
    -0.07
    ボー
    -0.07
     pussy
    -0.07
    ﻱ
    -0.07
    ungs
    -0.07
     accused
    -0.07
    uitable
    -0.07
     martin
    -0.07
    POSITIVE LOGITS
    真诚
    0.07
     McB
    0.07
    坚
    0.07
    omanip
    0.07
    cery
    0.07
    ⚡
    0.06
    堅
    0.06
    嘉年华
    0.06
    沧桑
    0.06
    antity
    0.06
    Act Density 0.043%

    No Known Activations