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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Distress
    0.44
     Start
    0.43
    IVES
    0.43
     Pang
    0.42
     Wind
    0.40
     Legend
    0.40
     Understanding
    0.40
    Wind
    0.40
    ↵↵
    0.39
     Long
    0.39
    POSITIVE LOGITS
    亗
    0.57
     ಮಾಡಿ
    0.51
     ṣ
    0.48
     кул
    0.48
    tica
    0.48
     rique
    0.47
    䐍
    0.47
     eru
    0.47
     ಸಲ
    0.46
     মিশ
    0.46
    Act Density 0.001%

    No Known Activations