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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Ster
    0.78
     Kiểm
    0.73
    י
    0.70
    䏲
    0.69
    Política
    0.69
     SOURCE
    0.68
    🕍
    0.67
    ודי
    0.66
    PhysRev
    0.65
    㡱
    0.65
    POSITIVE LOGITS
    стный
    0.79
    所以我
    0.73
    abhave
    0.72
    se
    0.71
     sehingga
    0.71
     എല്ലാവ
    0.71
     потер
    0.71
     będ
    0.70
    okhlov
    0.70
     أنه
    0.70
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.