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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     pathogen
    0.75
    physik
    0.73
    нской
    0.72
     thermodynamic
    0.71
     лучших
    0.70
     thisTrial
    0.70
    DanhMucSP
    0.70
    庁
    0.69
    炰
    0.69
    дии
    0.69
    POSITIVE LOGITS
     o
    0.89
    ily
    0.85
    inthe
    0.78
     na
    0.77
    news
    0.75
    l
    0.74
    output
    0.71
    aka
    0.71
     offre
    0.71
    ulter
    0.71
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.