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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     belül
    0.78
    ifient
    0.74
    क्या
    0.69
    ந்து
    0.66
    ጅ
    0.64
    pute
    0.62
     இத
    0.62
    égek
    0.62
    বরে
    0.60
     আর্থিক
    0.60
    POSITIVE LOGITS
     on
    3.49
     On
    2.81
    On
    2.74
     på
    2.73
     على
    2.68
     на
    2.65
     onto
    2.47
     auf
    2.44
     บน
    2.41
    บน
    2.39
    Act Density 1.122%

    No Known Activations