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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ഭം
    0.90
     ගැනීම
    0.86
    чество
    0.85
    теры
    0.80
    ணம்
    0.80
    믈
    0.80
    োলজি
    0.79
     Descriptor
    0.79
    ణం
    0.78
    දය
    0.77
    POSITIVE LOGITS
    적인
    2.16
    istic
    2.13
    ful
    1.76
    的な
    1.75
    性的
    1.66
    orous
    1.60
    ocratic
    1.57
    acious
    1.54
    ized
    1.54
    적
    1.50
    Act Density 1.508%

    No Known Activations