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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     syn
    -0.07
    㐱
    -0.07
    .syn
    -0.07
     ratio
    -0.07
    ণ
    -0.06
    脸
    -0.06
    ა
    -0.06
    כוונ
    -0.06
     sne
    -0.06
    道
    -0.06
    POSITIVE LOGITS
    TextEdit
    0.07
    ڍ
    0.07
    火焰
    0.07
     Muhammad
    0.07
    瓠
    0.06
     Playlist
    0.06
    陟
    0.06
    牵挂
    0.06
    ="'+
    0.06
    obile
    0.06
    Act Density 0.092%

    No Known Activations