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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    サン
    0.56
    lerine
    0.55
    大きい
    0.55
    ط
    0.54
    lerini
    0.54
     אני
    0.54
    ಮ
    0.54
    り
    0.54
    必要な
    0.52
    도
    0.52
    POSITIVE LOGITS
    y
    0.66
    in
    0.64
    (
    0.58
    .
    0.57
    e
    0.55
    aa
    0.54
    ie
    0.52
    ine
    0.51
    inja
    0.51
    inna
    0.51
    Act Density 4.481%

    No Known Activations