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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    as
    1.26
    d
    1.24
    د
    1.18
    es
    1.13
    ্ক
    1.13
     osoba
    1.12
    k
    1.12
     remodeling
    1.11
     göst
    1.10
    нага
    1.10
    POSITIVE LOGITS
    ⚈
    1.17
     severed
    1.16
    achd
    1.11
    ך
    1.10
     Wight
    1.09
     Sterile
    1.07
    ifferenti
    1.07
    UseDebug
    1.07
    kernels
    1.06
     Familiar
    1.06
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.