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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    andest
    -0.08
     incap
    -0.08
    ,"↵
    -0.07
     firefight
    -0.07
    胸口
    -0.07
     Gór
    -0.07
    的第一
    -0.07
    _Ph
    -0.07
     BEN
    -0.07
    🍞
    -0.06
    POSITIVE LOGITS
    large
    0.07
    imageView
    0.07
    -mult
    0.07
    袁
    0.07
    Css
    0.07
     userService
    0.07
    马来西亚
    0.07
    .vars
    0.06
    ℰ
    0.06
     multicultural
    0.06
    Act Density 0.014%

    No Known Activations