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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     multa
    0.45
    bia
    0.44
    trom
    0.42
    ೋಟ
    0.41
    ബൈ
    0.40
     Trom
    0.40
     trom
    0.39
     красный
    0.38
    ɓ
    0.38
    itius
    0.38
    POSITIVE LOGITS
     Flint
    1.08
     flint
    0.89
     Fred
    0.61
     Jets
    0.61
     Stone
    0.59
    Fred
    0.58
    Stone
    0.56
    Jet
    0.56
    Jets
    0.56
     Bed
    0.55
    Act Density 0.001%

    No Known Activations