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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ترنت
    0.77
    قد
    0.74
     kurze
    0.73
     kebakaran
    0.70
    {
    0.69
     crossing
    0.68
     billy
    0.66
    فاظ
    0.66
    くれる
    0.66
    دور
    0.66
    POSITIVE LOGITS
    há
    1.10
    a
    0.96
    h
    0.96
    hig
    0.91
    RAC
    0.91
    hiv
    0.90
     tabulated
    0.90
    ue
    0.90
     prong
    0.90
    at
    0.89
    Act Density 0.003%

    No Known Activations