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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    of
    1.06
    en
    1.02
     as
    1.02
     Usted
    0.98
     vergang
    0.98
    z
    0.95
     wilde
    0.94
    functie
    0.94
     \
    0.93
     vzděl
    0.91
    POSITIVE LOGITS
    ado
    1.27
    4
    1.27
    3
    1.26
    5
    1.26
    К
    1.20
    ৬
    1.19
    6
    1.14
    них
    1.11
    Г
    1.10
    Α
    1.08
    Act Density 0.000%

    No Known Activations