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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    м
    2.33
    ihilation
    1.88
    깐
    1.82
     lòng
    1.82
     coma
    1.79
    vasena
    1.78
     일어나
    1.70
    yat
    1.67
    仃
    1.67
    йом
    1.66
    POSITIVE LOGITS
    ℍ
    2.41
    valid
    2.40
    2.39
     hogy
    2.37
    P
    2.29
    शीर
    2.27
    %%%%%%%%%%%%
    2.27
    Razor
    2.25
    ለያዩ
    2.21
    ाइल
    2.20
    Act Density 0.003%

    No Known Activations