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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ॉन
    0.39
     stone
    0.38
     aus
    0.38
     Er
    0.37
    Events
    0.37
    Dog
    0.37
    нович
    0.37
    events
    0.36
     ограничи
    0.36
    delta
    0.36
    POSITIVE LOGITS
    %%\
    0.46
    📀
    0.44
    čenje
    0.41
     caries
    0.40
    цией
    0.40
     กว่า
    0.40
    👜
    0.40
    ሃኒ
    0.40
    !!!!!
    0.39
     modals
    0.39
    Act Density 0.008%

    No Known Activations