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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    跱
    -0.07
    GIN
    -0.07
    NEW
    -0.07
    _ICON
    -0.06
    .setOnAction
    -0.06
    Heroes
    -0.06
     geopol
    -0.06
     שת
    -0.06
    党史
    -0.06
     overflowing
    -0.06
    POSITIVE LOGITS
    的问题
    0.07
    rites
    0.07
    idos
    0.07
    ibles
    0.07
    שלח
    0.07
     Büro
    0.07
    撇
    0.06
     es
    0.06
    .array
    0.06
    brush
    0.06
    Act Density 0.012%

    No Known Activations