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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     instruction
    0.75
     achievement
    0.75
     addiction
    0.73
     initialization
    0.68
     socialization
    0.66
     accomplishment
    0.66
    യ
    0.66
     întreb
    0.65
     Guides
    0.64
     socializing
    0.62
    POSITIVE LOGITS
    িশালী
    0.85
    estimated
    0.82
     Tomas
    0.82
    imple
    0.79
    Thor
    0.76
     PML
    0.76
    ₮
    0.76
     Elisa
    0.75
     Prothorax
    0.74
     dona
    0.73
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.