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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     {{{
    1.04
    たら
    1.04
    てください
    1.03
    t
    1.00
    今の
    0.99
    dict
    0.99
    暴
    0.95
    使
    0.95
     (((
    0.94
    っと
    0.94
    POSITIVE LOGITS
     தமிழ்நாடு
    1.39
    anha
    1.28
    antiated
    1.28
    resolved
    1.28
     neque
    1.24
     pertenc
    1.23
    вторых
    1.21
     differentiable
    1.19
    ారణ
    1.19
    忪
    1.18
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.