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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ik
    1.19
    ర్చ
    1.02
    ák
    0.97
     lua
    0.94
     ausführ
    0.94
    ുന്ന
    0.93
    hensive
    0.93
     articoli
    0.93
    憐
    0.92
     dexterity
    0.92
    POSITIVE LOGITS
    weight
    0.99
     obese
    0.97
    BMI
    0.95
     khỏe
    0.94
     Weight
    0.92
    pregnant
    0.92
     Obesity
    0.91
     BMI
    0.90
     obesidad
    0.90
     obesity
    0.89
    Act Density 0.450%

    No Known Activations