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

    Neuronpedia

    INDEX
    Explanations

    words starting with Mag

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Apica
    0.45
     biased
    0.44
    粳
    0.44
     MTA
    0.42
     bias
    0.41
     RAC
    0.40
     fissure
    0.40
     RESOURCES
    0.39
    掾
    0.39
    鱻
    0.39
    POSITIVE LOGITS
     mag
    0.60
     magnetic
    0.58
     mágico
    0.56
     magical
    0.55
     магнит
    0.52
    mag
    0.51
     mág
    0.50
    魔法
    0.50
     маги
    0.50
    ister
    0.47
    Act Density 0.002%

    No Known Activations