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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     the
    0.56
     other
    0.50
     das
    0.50
     it
    0.48
     la
    0.47
    ,
    0.46
     with
    0.46
     that
    0.45
     this
    0.44
     e
    0.43
    POSITIVE LOGITS
    ácie
    0.51
    <unused2088>
    0.50
    kových
    0.50
    <unused465>
    0.50
    <unused414>
    0.49
    <unused450>
    0.49
    ляць
    0.49
    <unused1846>
    0.48
    <unused1064>
    0.48
    <unused2058>
    0.48
    Act Density 5.302%

    No Known Activations