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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     coles
    0.70
     бабу
    0.67
     welkom
    0.60
     cinn
    0.60
    usize
    0.59
    mathspace
    0.59
    羢
    0.59
    μάτων
    0.59
     أيضاً
    0.58
    氰
    0.58
    POSITIVE LOGITS
     NONE
    0.66
     None
    0.58
     wyłącznie
    0.57
    none
    0.54
     Highest
    0.54
     όχι
    0.52
     исключительно
    0.51
     Angriff
    0.51
     none
    0.51
     उच्चतम
    0.51
    Act Density 0.118%

    No Known Activations