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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    นะ
    0.84
     filha
    0.82
     ได้
    0.80
     ขนาด
    0.80
     października
    0.79
     จำนวน
    0.79
    ˹
    0.79
     reaffirm
    0.79
    แนะนำ
    0.78
    ª
    0.78
    POSITIVE LOGITS
    s
    0.79
    ن
    0.79
    j
    0.77
     personnelles
    0.77
    ج
    0.76
    लिया
    0.72
    𝐣
    0.72
     internals
    0.71
    t
    0.70
    स
    0.68
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.