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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     loyal
    1.28
     polluting
    1.18
     fossil
    1.16
     cz
    1.12
    暴力
    1.12
    RAL
    1.10
    剷
    1.09
     neonatal
    1.08
     kerajaan
    1.08
     regra
    1.07
    POSITIVE LOGITS
    ت
    1.42
    ために
    1.32
    an
    1.30
    floxacin
    1.24
    ość
    1.20
    a
    1.19
    able
    1.19
    $("
    1.17
    iye
    1.17
    zwe
    1.17
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.