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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     attenzione
    0.97
    ים
    0.88
    𝙫
    0.86
    ség
    0.85
    Dylan
    0.80
    Provence
    0.79
    robin
    0.78
    טים
    0.75
     vre
    0.74
    ات
    0.74
    POSITIVE LOGITS
    й
    1.01
     Этот
    0.85
     Tento
    0.85
    е
    0.81
     Это
    0.80
    ยนต์
    0.77
     Red
    0.76
     Hence
    0.75
     Эти
    0.75
     চক্র
    0.73
    Act Density 0.001%

    No Known Activations