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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     deputado
    1.45
    jx
    1.42
     histórias
    1.38
     świata
    1.37
    tes
    1.34
     olhando
    1.30
     pux
    1.28
    ský
    1.28
     vân
    1.27
    tre
    1.27
    POSITIVE LOGITS
     described
    1.27
     describes
    1.22
     넣
    1.21
     intended
    1.17
     handling
    1.14
     undergoes
    1.14
     identified
    1.13
     confirms
    1.12
     identifies
    1.12
     deposited
    1.12
    Act Density 0.000%

    No Known Activations