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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     personalmente
    0.55
    override
    0.51
    got
    0.50
    go
    0.50
    link
    0.50
     социа
    0.50
    за
    0.49
    bitcoin
    0.49
    ق
    0.48
    opens
    0.48
    POSITIVE LOGITS
     '&
    0.49
     മഹ
    0.47
     '[
    0.45
    }--\
    0.44
     breeder
    0.42
     Modular
    0.42
     Selective
    0.42
     '^
    0.42
     leaky
    0.42
     thermally
    0.41
    Act Density 0.003%

    No Known Activations