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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    й
    1.12
    $_{
    1.09
    ۟
    1.07
    𝚓
    1.02
    џ
    1.01
     helpless
    1.00
    LuaPush
    0.99
    оборот
    0.97
    ј
    0.97
    zPosition
    0.96
    POSITIVE LOGITS
     Rfe
    1.19
     aria
    1.08
    nep
    1.04
    light
    1.02
    Res
    1.00
     LTD
    0.98
    Koch
    0.97
     subgroups
    0.95
    AN
    0.95
     aversion
    0.94
    Act Density 0.000%

    No Known Activations