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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     thickness
    0.40
     크게
    0.38
    isive
    0.38
    大きく
    0.37
     مرك
    0.37
     क्रिसमस
    0.36
     modulate
    0.36
     brightness
    0.35
    რივ
    0.35
     प्रतिभाशाली
    0.35
    POSITIVE LOGITS
    ্লো
    0.40
    ปัจ
    0.37
    ISSU
    0.37
     аре
    0.36
    ésia
    0.36
     sank
    0.35
    ố
    0.35
     уде
    0.35
    गरानी
    0.35
    ल्लिंग
    0.35
    Act Density 0.000%

    No Known Activations