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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Really
    0.50
    Depend
    0.44
    Difference
    0.44
     війни
    0.44
    真的
    0.42
    icity
    0.42
    There
    0.41
    weapon
    0.41
    peas
    0.41
     ailment
    0.41
    POSITIVE LOGITS
     interesante
    0.54
     Oro
    0.53
    ;%%
    0.52
     intéressant
    0.51
     Lightning
    0.49
    న్స్
    0.47
    的市场
    0.47
     Industria
    0.46
     assuring
    0.45
     Carrying
    0.45
    Act Density 0.001%

    No Known Activations