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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     nouveaux
    0.41
     agglomer
    0.39
     leaked
    0.36
     nouveau
    0.35
     cancerous
    0.35
    iyaç
    0.34
     cô
    0.34
     Pokémon
    0.33
    ገልግሎ
    0.33
     ce
    0.33
    POSITIVE LOGITS
    ⓞ
    0.52
     selaku
    0.50
     trouxe
    0.47
     двумя
    0.45
     подробно
    0.45
    ρία
    0.45
    🌗
    0.44
    謖
    0.43
    กับ
    0.43
     стрельца
    0.43
    Act Density 0.013%

    No Known Activations