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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     떨어
    0.65
     décès
    0.61
    éssel
    0.61
    の変化
    0.60
     personn
    0.60
    ърква
    0.59
    orkan
    0.59
     displeasure
    0.58
     predic
    0.58
     गुस्से
    0.58
    POSITIVE LOGITS
    SizeBytes
    0.70
    manager
    0.70
    map
    0.66
    marks
    0.64
    flows
    0.63
    カイブ
    0.62
    builder
    0.62
     Minecraft
    0.61
    ID
    0.60
    folder
    0.60
    Act Density 0.000%

    No Known Activations