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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ből
    1.55
    manship
    1.48
    kswagen
    1.47
    britannien
    1.44
    dra
    1.42
    س
    1.41
    ifies
    1.39
    dade
    1.39
    erweise
    1.38
    kannya
    1.36
    POSITIVE LOGITS
    ⃣
    1.34
    ️⃣
    1.28
    THING
    1.25
    .
    1.16
     esper
    1.13
    }));
    1.13
     reqParams
    1.08
    /;
    1.06
     nhằm
    1.05
    它們
    1.05
    Act Density 0.337%

    No Known Activations