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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     in
    0.49
     CL
    0.49
    ف
    0.46
     In
    0.46
     blood
    0.45
     It
    0.45
     ability
    0.44
     \
    0.43
     remove
    0.42
     main
    0.42
    POSITIVE LOGITS
    ous
    0.58
    ombre
    0.56
    iphy
    0.54
    oy
    0.52
    osity
    0.51
    íe
    0.51
    aves
    0.50
    Celeron
    0.50
    íes
    0.49
     pariy
    0.49
    Act Density 0.000%

    No Known Activations